The path toward realizing next-generation petascale and exascale computing is increasingly dependent on building supercomputers with unprecedented numbers of processors. To prevent the interconnect from dominating the overall cost of these ultrascale systems, there is a critical need for scalable interconnects that capture the communication requirements of ultrascale applications. It is, therefore, essential to understand high-end application communication characteristics across a broad spectrum of computational methods, and utilize that insight to tailor interconnect designs to the specific requirements of the underlying codes. This work makes several unique contributions toward attaining that goal. First, we conduct one of the broadest studies to date of high-end application communication requirements, whose computational methods include: finite difference, lattice Boltzmann, particle-in-cell, sparse linear algebra, particle-mesh ewald, and FFT-based solvers. Using derived communication characteristics, we next present the fit-tree approach for designing network infrastructure that is tailored to application requirements. The fit-tree minimizes the component count of an interconnect without impacting application performance compared to a fully connected network. Finally, we propose a methodology for reconfigurable networks to implement fit-tree solutions. Our Hybrid Flexibly Assignable Switch Topology (HFAST) infrastructure, uses both passive (circuit) and active (packet) commodity switch components to dynamically reconfigure interconnects to suit the topological requirements of scientific applications. Overall, our exploration points to several promising directions for practically addressing the interconnect requirements of future ultrascale systems. 相似文献
In this paper, we compare the performance of dispatching rules in a real-life job shop environment and provide guidance for schedulers to determine effective dispatching rules for this type of systems. We consider a total of 20 dispatching rules, that range from some previously developed rules to some recently developed sophisticated rules such as process time plus work in next queue plus negative slack (PT + WINQ + SL), multi factor rule, and bottleneck dynamics. The performance measures examined are average weighted tardiness and proportion of tardy jobs. Discrete event simulation model based on ARENA is developed to implement the rules. Results from this study are given in detail. 相似文献
The growth of the Internet and electronic commerce opens new venues for companies to create flexible supply chains by offering high-speed communication and tight connectivity. To take full advantage of these new opportunities, companies need to be able to respond quickly to opportunities as they arise and make smart decisions taking into account the vast amount of data now available. We describe a decision support system which helps companies in making decisions about purchasing, manufacturing or promotions, while considering supplies and demands posted on the Internet, in addition to their own inventory, capacity and demand. The decision support system is currently being tested within an electronic marketplace we built for paper products, which went online in September 1999. 相似文献
The acceptance and widespread use of the Android operating system drew the attention of both legitimate developers and malware authors, which resulted in a significant number of benign and malicious applications available on various online markets. Since the signature-based methods fall short for detecting malicious software effectively considering the vast number of applications, machine learning techniques in this field have also become widespread. In this context, stating the acquired accuracy values in the contingency tables in malware detection studies has become a popular and efficient method and enabled researchers to evaluate their methodologies comparatively. In this study, we wanted to investigate and emphasize the factors that may affect the accuracy values of the models managed by researchers, particularly the disassembly method and the input data characteristics. Firstly, we developed a model that tackles the malware detection problem from a Natural Language Processing (NLP) perspective using Long Short-Term Memory (LSTM). Then, we experimented with different base units (instruction, basic block, method, and class) and representations of source code obtained from three commonly used disassembling tools (JEB, IDA, and Apktool) and examined the results. Our findings exhibit that the disassembly method and different input representations affect the model results. More specifically, the datasets collected by the Apktool achieved better results compared to the other two disassemblers.
Designing and operating two-sided assembly lines are crucial for manufacturing companies which assemble large-sized products such as trucks, buses and industrial refrigerators. This type of assembly line structure has several advantages over one-sided assembly lines such as shortened line length and reduced throughput time. The research area has recently focused on balancing two-sided assembly lines owing to these advantages. However, due to the complex structure of this problem, some practical constraints have been disregarded or have not been fully incorporated. In order to overcome these deficiencies, a fully constrained two-sided assembly line balancing problem is addressed in this research paper. Initially, a mathematical programming model is presented in order to describe the problem formally. Due to the problem complexity, two different swarm intelligence based search algorithms are implemented to solve large-sized instances. Bees algorithm and artificial bee colony algorithm have been applied to the fully constrained two-sided assembly line balancing problem so as to minimize the number of workstations and to obtain a balanced line. An extensive computational study has also been performed and the comparative results have been evaluated. 相似文献
We study graph properties that admit an increasing, or equivalently decreasing, sequence of graphs on the same vertex set such that for any two consecutive graphs in the sequence their difference is a single edge. This is useful for characterizing and computing minimal completions and deletions of arbitrary graphs into having these properties. We prove that threshold graphs and chain graphs admit such sequences. Based on this characterization and other structural properties, we present linear-time algorithms both for computing minimal completions and deletions into threshold, chain, and bipartite graphs, and for extracting a minimal completion or deletion from a given completion or deletion. Minimum completions and deletions into these classes are NP-hard to compute. 相似文献
Cationic liposome-DNA complexes are being evaluated as potential gene therapy agents for the lung. Cations have strong effects
on the biophysical functions of lung surfactant. Therefore, we assessed whether cationic liposomes [composed of N-(1-(2,3-dioleyloxy) propyl)-N,N,N-trimethyl-ammonium chloride and dioleylphosphatidylethanolamine] with or without DNA affect behavior of four types of surfactant
in vitro. Experiments were carried out using a modified Wilhelmy surface balance. The ability of surfactants that contain protein
and anionic lipids to lower surface tension was inhibited in the presence of cationic liposomes. Inactivation was less when
DNA was preincubated with cationic liposomes. Surfactant that contained neither protein nor anionic lipids was not inactivated.
Mechanical properties of the lung were studied to assess in vivo surfactant function after intratracheal instillation of a cationic liposome-DNA complex into adult rats. Pressure-volume
deflation curves were shifted by 18% compared with those from normal (untreated) animals, but this effect was transient and
not different from that observed in animals who received a similar volume of saline. These findings indicate that cationic
liposomes alone may have deleterious effects on behavior of some surfactants possibly by disrupting charge interactions between
negatively charged phospholipids and surfactant proteins. When DNA is added to liposomes before exposure to surfactants, the
adverse charge interactions may be obviated by charge neutralization of liposomes by DNA. 相似文献
Despite the significant progress made in the field of electrochromic polymers, the multichromic facility of current knowledge is restricted. Therefore, as previously proven, electrochemical copolymerization of 1-benzyl-2,5-di(thiophen-2-yl)-1H-pyrrole (SNBS) and 3,4-ethylenedioxythiophene (EDOT) was used as a strategy to achieve desired multichromic properties, where the resultant copolymer displayed distinct color changes between claret red, yellow, green, and blue colors with short switching times and high optical contrast. As an application, absorption/transmission type electrochromic device with indium tin oxide (ITO)/copolymer/gel electrolyte PEDOT/ITO configuration was constructed, where copolymer and PEDOT functioned as the anodically and the cathodically coloring layers, respectively. Results implied the successive use of this copolymer in electrochromic device applications, since the device exhibited short switching times with a wide color variation upon applied potential. 相似文献