Search

Effective team coordination is crucial for successful global software projects. Although considerable research effort has been made in this area, no agreement has been reached on the influence of dispersion on team coordination and performance. The objective of this paper is to summarize the evidence on the relationship among context dispersion, team coordination and performance in global software projects. We have performed a Systematic literature review (SLR) to collect relevant studies and a thematic analysis to synthesize the extracted data. We found 28 primary studies reporting the impact of five dispersion dimensions on team performance. Previously, only two primary studies considered and distinguished all of these dispersion dimensions in studying dispersed team performance. The dispersion dimensions affect team outcomes indirectly through influencing organic and mechanistic coordination processes. Empirical evidence show that geographical dispersion impacts negatively and temporal dispersion has a mixed effect on team performance. While studies with teams working across different time zones shows a tendency that the team performance is pessimistically perceived, studies that use direct measure on task performance shows a positive association to temporal dispersion. The paper provides implications for future research and practitioners in establishing effective distributed team coordination. [ABSTRACT FROM PUBLISHER]

In order to examine the relationship between ownership structure and firm performance of private companies, this paper selects 283 private companies listed in Two Exchanges in the period from 2008 to 2010. Ownership structure is described in two aspects: ownership concentration and equity properties. First, a new comprehensive performance index is obtained by principal component analysis method based on the financial indexes. Then the paper makes linear regression analysis of that new performance index and ownership structure. Empirical findings suggest that most of the sample companies are controlled by top five shareholders especially the first major shareholders; appropriate ownership concentration may benefit firm performance. Compared to the literature, we find that different from state-owned companies, the proportion of shares held by state or corporate has no significant effects on firm performance of private listed companies; tradable shareholders play almost no governing effect which has no change before or after nontradable shares reform. [ABSTRACT FROM PUBLISHER]

This paper presents a prototype for a virtual platform to estimate performance of OpenMP parallelized programs in shared-memory many-core platforms at early stages of the design flow. This is a challenging problem because, at these stages, the particular details of the final platform are unknown, but early performance estimations are needed to choose between different parallel implementations. The tool presented enables fast modelling of the SW and HW components in a complete platform model and also has the advantage of enabling configurable models of any many-core platform. This can be achieved because of two novel ideas that are explained in this paper: a native simulation framework that enables the modelling of concurrent threads described in OpenMP and a novel use of "shared" and "private" clauses that models the data transfers. The advantages of using the proposed tool are explained with a specific example. [ABSTRACT FROM PUBLISHER]

Traditional analysis on the TCP performance attributes the overhead of TCP mainly on these aspects: many times of memory access and copy, much data transmission on bus and a large number of CPU cycles required by the protocol processing. Compared to TCP, the main advantage of RDMA lies in its single memory access which brings a higher data transmission bandwidth and lower CPU utilization. However, the hardware platforms that these analyses are based on are already out-of-date from today's view. The key point is that TCP and RDMA performance can change with the rapid development of the computer architecture and computer hardware components. In this paper, we re-analysis the performance of TCP and RDMA on the modern server platform (e.g., multi-core), and we find that the upper limit of TCP transmission bandwidth has been greatly upgraded compared to the old platform. Besides, the compatibility and complexity problems in programming brought by RDMA technology are still serious. Based on this conclusion, we constructed a network platform which uses multi-thread technology and TCP protocol to achieve a high speed transmission bandwidth in the InfiniBand network environment. [ABSTRACT FROM PUBLISHER]

This paper proposes a novel client/server architecture known as Multi-client/Multi-server (MC/MS). MC/MS is an alternative to BitTorrent-like peer-to-peer systems, single source multiple mirrored techniques, and n-tier client and server protocol. The use of a peer-to-peer resource protocol increases network traffic and impacts all users on the network. In the MC/MS architecture, one client establishes a connection with one connection server, and concurrent data are dispatched from multiple data servers located on different subnets from each other. The data can be dispatched to the multiple clients anywhere on the network, which then reassemble or otherwise process the data. MC/MS distributes the data of a large file across multiple servers without any redundancy. The separation of data transfer from a connection establishment is entirely transparent to the client. It reduces network impact, avoids redundancy of data, and improves reliability of the system by avoiding a bottlenecks at both the server and client sides. MC/MS reduces transmission time up to 82% as compared to the conventional techniques. It also offers much better data transmission time than comparable BitTorrent systems in a LAN environment. This paper proposes a ‘mission-critical’ application as the motivation for this work. The paper describes a design and an initial implementation of the MC/MS architecture, and serves as a foundation for prospective application implementers. [ABSTRACT FROM PUBLISHER]

Previous comparison about localization accuracy of affine region detectors is focused on the overlap error between corresponding regions, which is not sufficient for some applications such as wide baseline matching, registration, structure from motion etc., in which localization accuracy in position is especially important. In this paper, we make a experimental comparison about the localization accuracy of position of CGR(Center of Gravity of Region) of the detected corresponding regions on a set of test images under varying conditions. Three methods of the state of the art in affine region detectors are included: MSER, Hessians Affine and Harris Affine. This comparison is complementary with previous similar work. The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression. [ABSTRACT FROM PUBLISHER]

Call Level Interfaces (CLI) play a key role in database applications whenever performance is a key requirement. SQL statements are encoded inside strings this way keeping the power and the expressiveness of the SQL language. Unfortunately, despite this significant advantage, CLI do not promote the development of business tier components, much less for business tier components driven by dynamic adaptation. To tackle this CLI drawback, and simultaneously keep their advantages, this paper proposes an architecture, herein referred to as the Object-to-Relational Component Architecture (ORCA), relying on CLI for building adaptable business tiers components. ORCA has the capacity of being dynamically adapted to manage any set of SQL statements deployed at runtime. The focus of this paper is threefold: 1) present the ORCA, 2) present a proof of concept based on Java and, finally, 3) assess its performance against a standard CLI. [ABSTRACT FROM PUBLISHER]

Recently, embedded multicore platforms have become popular, but software development for such platforms has been very challenging. While message-passing is a popular programming model for parallel applications, it is not adequately supported on the current embedded multicore platforms. Similar to the situations in '80s~'90s, applications are hardly portable across parallel computers before the advent of MPI. Unfortunately, MPI is too big for most embedded platforms of today. Moreover, the message-passing functions need to utilize the architectural features to offer optimized performance, but such platform-specific optimizations often hurt the portability. This paper addresses the portability and performance issues by designing a new message-passing library with a three-layer modular design. The top two layers are mostly platform-independent, and the bottom layer enables platform-specific optimizations. We discuss the performance issues in the paper and evaluate the issues with experimental results. [ABSTRACT FROM PUBLISHER]

Job scheduling is a critical mechanism which can significantly affect the performance of complex heterogeneous distributed systems, such as Grids. Since computational Grids are multi-criteria environments by nature, modern allocation algorithms should concern more than one criterion to produce scheduling solutions. In this paper, we propose a multi-criteria Genetic Algorithm, which tries to eliminate the security risks and power consumption of the system, in addition to the completion time of jobs. Although Genetic Algorithms are suitable for large search space problems such as job scheduling, they are too slow to be executed online. Hence, we changed the implementation of a traditional genetic algorithm, introducing the Accelerated Genetic Algorithm. In addition, Accelerated Genetic Algorithm with Overhead is also presented, which concerns the extra overhead caused by the application of Accelerated Genetic Algorithm. We propose the best combination of weights of each criterion of our Genetic Algorithm in order to maximize the performance of the system. Afterwards, Accelerated Genetic Algorithm and Accelerated Genetic Algorithm with Overhead are compared with three well-known heuristics. Simulation results indicate a substantial performance advantage of both Accelerated Genetic Algorithm and Accelerated Genetic Algorithm with Overhead. [ABSTRACT FROM PUBLISHER]

This paper focuses on the modeling of solar photovoltaic (PV) cell and the performance of typical solar PV panels in selected areas in the Sultanate of Oman. An accurate solar PV cell electrical model is based on the junction diode equations. The model consists of a photo-current current source, a single diode junction and a series resistance, and takes into account temperature and solar irradiation dependence. The model is developed using MATLAB/Simulink and is used to investigate the variation of the maximum power point for different temperatures and solar irradiation levels. Finally, the model is experimentally validated for a typical 30 Watt solar module connected to a variable load. [ABSTRACT FROM PUBLISHER]

Video popularity ranking is commonly used in various streaming systems. Existing popularity ranking systems usually rank videos from the perspective of access frequency and ignore other implicit feedback, due to the belief that popularity rankings with different implicit metrics are highly consistent. Based on a large collection of real-world system trace data, this paper systematically compares video popularity rankings with four different implicit metrics: access frequency, access user frequency, watching time, normalized watching time. We not only analyze the temporal dynamics of videos' popularities ranking with different metrics, but also examine the correlation between them. We have two main findings. 1) The popularities rankings with access frequency and watching time have strong correlation, but the other pairs have low consistency. 2) The temporal dynamics of daily rankings are similar, while the popularity rankings by access frequency and user number frequency are more stable than others. This paper also proposes a new top-N rank correlation coefficient and proves its efficiency. Our analysis results indicate that the implicit metric of popularity ranking needs to be carefully chosen according to specific applications. [ABSTRACT FROM PUBLISHER]

RF/wireless interconnect is an emerging technology for mitigating the problems of nano-scale metal wires in ultra-large integrated circuits. However, there is no EDA physical design flow for using this technology in conventional application specific ICs. In this paper, an architecture containing both wired and wireless interconnects is presented for regular ASICs corresponding with assignment and placement algorithms for RF-interconnect resources. Experimental results show that total wirelength (routing congestion) and critical delay of attempted benchmarks is reduced by 16.8% and 30.1% on average, respectively. These benefits are earned in the cost of 2.33% area and 11.89% power consumption overhead for large circuits. Moreover, paper concludes that the area and power consumption overheads are lower considerably when the size of design grows. [ABSTRACT FROM PUBLISHER]

Cache size is a scarce resource in multi processors systems, Scheduling has a dramatic impact on the delay introduced by cache contention. This paper investigates the effects between programs running on a multi processors system, considering cache contention. This paper is proposed in low load case, the most programs' number of each core is one. The goal is to reduce cache contention between threads, improve the performance of processor and shorten the execution time, to achieve the goal of reducing energy consumption. [ABSTRACT FROM PUBLISHER]

Sensors are used to monitor certain aspects of the physical or virtual world and databases are typically used to store the data that these sensors provide. The use of sensors is increasing, which leads to an increasing demand on sensor data storage platforms. Some sensor monitoring applications need to automatically add new databases as the size of the sensor network increases. Cloud computing and virtualization are key technologies to enable these applications. A key issue therefore becomes the performance of virtualized databases and how this relates to physical ones. Traditional SQL databases have been used for a long time and have proven to be reliable tools for all kinds of applications. NoSQL databases have gained momentum in the last couple of years however, because of growing scalability and availability requirements. This paper compares three databases on their relative performance with regards to sensor data storage: one open source SQL database(PostgreSQL) and two open source NoSQL databases (Cassandra and MongoDB). A comparison is also made between running these databases on a physical server and running them on a virtual machine. A minimal sensor data structure is used and tested using four operations: a single write, a single read, multiple writes in one statement and multiple reads in one statement. [ABSTRACT FROM PUBLISHER]

Traditional EDA flows are made up of different point tools stitched together to progress from higher levels of design abstraction to physical level chip details. Data, intent, and constraints are passed on through this flow via intermediate text files. Some of these files such as the Standard Delay Format (SDF) files, are significantly large in size, and may run into gigabytes. Parsing of these files is a challenge. Core EDA algorithms have more recently started embracing the concept of parallelism using multi-core processors. This has started increasing the contribution of the time taken by the parser in the whole flow, increasing the need to improve the parser performance. The authors propose a methodology for efficient multi-threading of parsers in EDA in [2]. This paper is a companion paper detailing the application of the methodology on the Synopsys SDF Parser. Performance improvements in the range of 4X on 8-core machines was observed on implementing this methodology. [ABSTRACT FROM PUBLISHER]

Security in embedded systems has become a main requirement in modern electronic devices. The demand for low-cost and highly secure cryptographic algorithms is increasingly growing in fields such as mobile telecommunications, handheld devices, etc. In this paper, we analyze and evaluate the development of cheap and relatively fast hardware implementations of the KATAN family of block ciphers. KATAN is a family of six hardware oriented block ciphers. All KATAN ciphers share an 80-bit key and have 32, 48, or 64-bit blocks. We use VHDL under Altera Quartus in conjunction with ModelSim to implement and analyze our hardware designs. The developed designs are mapped onto high-performance Field Programmable Gate Arrays. We compare our findings with similar hardware implementations and C software versions of the algorithms. The performance analysis of the C implementations is done using Intel Vtune Amplifier running on Dell precision T7500 with its dual quad-core Xeon processor and 24 GB of RAM. The obtained results show better performance when compared with existing hardware and software implementations. [ABSTRACT FROM PUBLISHER]

WiFi networks have become ubiquitously deployed. Anecdotal evidence suggests that wireless networks are less secure than wired networks. However, very little quantitative data exists to characterize the insecurity levels of WiFi networks. In this paper, we take a first look at city-level WiFi security statistics for eighteen cities within the United States. For the purposes of this study, we define unsecure WiFi networks as those that do not use WEP, WPA2 or any WiFi security standard. We found that on average, 45 percent of WiFis studied were insecure, with Miami, FL having 81 percent of WiFi networks unsecure. We also found that Texas had several cities with a high number of blacklisted IP addresses. In the end, we found no strong correlation between WiFi insecurity rates and blacklisting rates, which we attribute to inadequate education of the inhabitants of cities on how to report malicious activity so that perpetuators can be blacklisted. Finally, we found that the percentage of secure WiFi networks in cities with municipal WiFi networks was comparable to that of cities without municipal WiFi networks. [ABSTRACT FROM PUBLISHER]

JavaScript is the dominant language for implementing dynamic web pages in browsers. Even though it is standardized, many browsers implement language and browser bindings in different and incompatible ways. As a result, a plethora of web development frameworks were developed to hide cross-browser issues and to ease development of large web applications. An unwelcome side-effect of these frameworks is that they can introduce memory leaks, despite the fact that JavaScript is garbage collected. Memory bloat is a major issue for web applications, as it affects user perceived latency and may even prevent large web applications from running on devices with limited resources. In this paper we present JSWhiz, an extension to the open-source Closure JavaScript compiler. Based on experiences analyzing memory leaks in Gmail, JSWhiz detects five identified common problem patterns. JSWhiz found a total of 89 memory leaks across Google's Gmail, Docs, Spread-sheets, Books, and Closure itself. It contributed significantly in a recent effort to reduce Gmail memory footprint, which resulted in bloat reduction of 75% at the 99th percentile, and by roughly 50% at the median. [ABSTRACT FROM PUBLISHER]

As a multi-layer forwarding network, the back propagation neural network (BPNN) with manifold derived structures has been most widely used in artificial intelligence applications. Based on the given non-linear system and the BPNNs of varying internal structures, this paper quantitatively reports the findings in the correlation between the number of hidden layers and the BPNN performance. The selection of learning rate is also investigated using the 3-layer BPNN and the same non-linear system. Through the simulation results in this probe it finds that the BPNN performance is not improved notably or even degraded with the increase of hidden layers, and 3-layer (or 1-1-1) BPNN is identified as the best performer. [ABSTRACT FROM PUBLISHER]

Lustre has been widely used in mass storage systems. Its performance study also increasingly widely. During the analyzing of lustre system, this paper proposes the several important factors which can influence the system performance. From the test results we can find that: according to different Lustre application, network transmission medium, strip numbers and client numbers has a very high price for configuration. [ABSTRACT FROM PUBLISHER]

The SAT-AIS technology, which offers global ship traffic monitoring from low earth orbit, is steadily gaining more attention within groups of communication hardware designers, as well as among safety policy chairman. Numerous research and business groups are elaborating hardware solutions. Motivated by testing needs as a result of the upcoming DLR AIS satellite-mission AISat, a dedicated AIS Testbed for Satellite Systems was developed. This paper describes the approaches and procedures, which were identified as the most significant for testing SAT-AIS hardware. [ABSTRACT FROM PUBLISHER]

As computing devices absorb more of our computing needs and the energy crisis continues, specialized hardware is being built with energy conservation in mind. In particular, processor manufacturers keep increasing the number of cores and are now moving to heterogeneous multi-core processors. In this paper we propose PATA (Performance-Asymmetric Thread Assignment) algorithm for heterogeneous core systems composed of ``big'' high-performance and ``small'' low-power cores. The PATA algorithm makes thread-to-core assignments decisions at runtime based on the threads' IPS (Instructions committed Per Second), periodically allocating the available big cores to threads with current highest IPS, in order to exploit the different threads' execution phases. We implemented and evaluated PATA in a real multi-core system running Linux, where core heterogeneity was emulated using different clock speed (dynamic frequency scaling). Our results show that PATA provides the best performance when compared with standard Linux scheduler and the state-of-art IPS-driven algorithm. [ABSTRACT FROM PUBLISHER]

MPI implementations typically equate an MPI process with an OS-process, resulting in a coarse-grain programming model where MPI processes are bound to the physical cores. Fine-Grain (FG-MPI) extends the MPICH2 implementation of MPI and implements an integrated runtime system to allow multiple MPI processes to execute concurrently inside an OS-process. FG-MPI's integrated approach makes it possible to add more concurrency than available parallelism, while minimizing the overheads related to context switches, scheduling and synchronization. In this paper we evaluate the benefits of added concurrency for cache awareness and message size and show that performance gains are possible by using FG-MPI to adjust the grain-size of a program to better fit the cache and potential advantages in passing smaller versus larger messages. We evaluate the use of FG-MPI on the complete set of the NAS parallel benchmarks over large problem sizes, where we show significant performance improvement (20%-30%) for three of the eight benchmarks. We discuss the characteristics of the benchmarks with regards to trade-offs between the added costs and benefits. [ABSTRACT FROM PUBLISHER]

This paper presents MoCCA — a cellular cloud architecture for building mobile clouds using small-footprint micro-servers running on cell phones. We provide details of this architecture which is based on GSM standard, discuss several challenges, and include performance results to validate the assumptions that a mobile cellular cloud can indeed be in the realm of possibilities. [ABSTRACT FROM PUBLISHER]

The mobile ad hoc networks (MANET) technology is a self organized wireless interconnection of communication devices without the use of any fixed network infrastructure/backbone. The performance of Ad-hoc On-demand Distance Vector (AODV) and Dynamic Source Routing (DSR) protocol are two MANET protocol. This paper presents the performance analysis comparison of ad-hoc on-demand routing protocol (AODV) and Dynamic Source Routing (DSR) under different performance metrics like throughput, packet drop rate and end-to-end delay. The simulation result shows that throughput of AODV protocol is better than DSR protocol as the nodes are increasing/adding to network. Packet drop rate and end-to-end delay of AODV protocol is less than DSR protocol as the nodes are increasing. Efficiency achieved by the AODV protocol is higher than DSR protocol in mobile ad hoc networks. The simulation is done in Network Simulator (NS) 2. [ABSTRACT FROM PUBLISHER]

Three stakeholders come into play in peer-to-peer (P2P) video-on-demand (VoD), namely peers/viewers, content providers and ISPs. Different design choices have been proposed to improve quality of user experience, to bring down content server bandwidth cost and to reduce ISP-unfriendly traffic. However, it is unclear whether the ability of these design choices to meet interests of one stakeholder comes at the expense of their ability to satisfy the other stakeholders. Yet, another question remains open for two different types of mesh-based P2P VoD protocols: How well do the regular P2P VoD protocol and the network coding-based P2P VoD protocol perform compared to each other? In this paper, we present a simple performance versus cost framework (PCF) to evaluate impact of different design choices. Via detailed PCF-based simulations, we compare the two P2P VoD protocols and show that the two protocols each has its own territory on which it excels at efficiency. We reveal many important findings about P2P VoD design and hope they are useful to P2P VoD designers. [ABSTRACT FROM PUBLISHER]

Improving performance of Web services interactions is an important factor to burst the adoption of SOAin mission-critical applications, especially when they deal with large business objects whose transfer time is not negligible. Designing messages dynamic granularity (offloading) is a key challenge for achieving good performances. This requires the server being able to predict the pieces of data actually used by clients in order to send only such data. However, exact prediction is not easy, and consequently lazy interactions are needed to transfer additional data whenever the prediction fails. To preserve semantics, lazy accesses to the results of a Web service interaction need to work on a dedicated copy of the business object stored as application state. Thus, dynamic offloading can experience an overhead due to a prediction failure, which is the sum of round-trip and storage access delays, which could compromise the benefits of the technique. This paper improves our previous work enabling dynamic offloading for both IN and OUT parameters, and analyses how attributes copies impact on the technique, by comparing the overheads introduced by different storage technologies in a real implementation of a Web services framework that extends CXF. More specifically, we quantitatively characterize the execution contexts that make dynamic offloading effective, and the expected accuracy of the predictive strategy to have a gain in term of response time compared to plain services invocations. Finally, the paper introduces the Attribute Loading Delegation technique that enables optimized data-transfers for those applications where data-intensive multiple-interactions take place. [ABSTRACT FROM PUBLISHER]

3D ICs are emerging as a promising solution for scalability, power and performance demands of next generation Systems-on-Chip (SoCs). Along with the advantages, it also imposes a number of challenges with respect to cost, technological reliability, thermal budget and so forth. Networks-on-chip (NoCs), which is thoroughly investigated in 2D SoCs design as scalable interconnects, is also well relevant to 3D IC Design. The cost of moving from 2D to 3D should be justified with improvements in performance, power or latency. To solve this problem, this paper presents a new simulation framework for 3D NoCs. We established a new Generic Scalable Pseudo Application (GSPA), where user can generate their own scalable pseudo applications. We have also integrated the state-of-the-art benchmarks to evaluate the 3D NoC system. In the framework, the 3D NoC with different vertical channel densities (VD) (i.e. number of Through-Silicon-Vias (TSVs)) can be generated according to the preference of users. After the simulation, the power consumption and system performance are evaluated. We have compared 2D NoC architecture with 3D NoC architecture with different VDs. The experimental results show that 3D architectures have significant advantage (Avg. 51%, 44%, 35% for 100%, 50%, 25% VD, respectively) in the aspect of interconnect power delay product in comparison to 2D mesh architecture. The 25% VD architecture is the best choice with 17% advantage over full connection (100% VD) 3D NoC architecture in the aspect of Figure of Merit which takes area and TSV connection yield into account among all the experiments for the given constrains. [ABSTRACT FROM PUBLISHER]

The move towards broadband converged networks and applications is increasing the need for advanced network monitoring. As the EPC will completely overhaul the classic GPRS architecture by replacing it with a much flatter all-IP network; it will become a single converged core handling all applications including the existing telephony services. In this context, application performance monitoring will be essential in order to measure the user experience and to get more insight into the traffic trends and applications usage. In this paper, we will discuss the challenges facing network monitoring in EPC and provide recommendations in this regard. [ABSTRACT FROM PUBLISHER]

Considering the accelerating rate at which software application development is progressing, emerging technologies like Scala, Ruby, and Groovy almost run in a neck to neck competition. This paper presents our study of these languages which are most commonly used in telecommunication/ middleware video streaming applications as compared to the long standing Python technology. [ABSTRACT FROM PUBLISHER]

This paper presents a distributed run-time task synchronization method for multicore processors aiming to reduce the average power consumption of the chip and satisfy a given thermal constraint, while imposing no performance overhead. Being built on the game theory concepts, this is achieved by dynamically changing the frequency of each individual core based on its current workload iteratively until converging to an optimal point. In this work we target two thermal constraints: keeping (1) the core peak temperature and, (2) thermal gradient across the cores below a predefined threshold. The results show that the proposed framework can find the appropriate frequency for each core based on the optimization target, within an acceptable time. [ABSTRACT FROM PUBLISHER]

Assessing the impact of Mandatory Access Control (MAC) integration in the Linux kernel performance is still an open problem. Regarding the specific paradigm of MAC in High Performance Computing, there are actually few works. Yet, guaranteeing security properties on a shared cluster is both a necessity and a challenge. This is a necessity because it is mandatory to ensure the confidentiality and integrity of data computed by the users, and a challenge because a cluster is a costly resource built with performance in mind. This paper deals with the need to integrate MAC in Linux-based operating systems for HPC clusters in an efficient way. [ABSTRACT FROM PUBLISHER]

Power consumption in large scale systems has been studied severely. Reasons are mainly environmental-ecological and economical. This paper studies the application of power saving mechanisms combined with scheduling policies in a real-time 2-level heterogeneous grid system. We propose power saving mechanisms taking advantage of Dynamic Voltage Scaling of modern processors. A simulation model is used to evaluate performance of these policies at the grid level and at the local level and to measure the energy saved by the application of power-saving mechanisms at the processor level. Our experimental results show 15% to 35% savings in processors¢ power consumption when the power saving mechanism is applied, while performance of the system is maintained at satisfactory levels. [ABSTRACT FROM PUBLISHER]

As one of the four major applied areas, E-commerce of tourism enterprise's performance has drawn scholars' attention gradually. For such purpose, this paper constructs an index system which evaluates e-commerce maturity of tourism enterprise based on five elements (infrastructure construction, behavior of e-commerce, business improvement, security of e-commerce and benefit of e-commerce), and finds out the element which needed to be strengthened by using Delphi algorithm to determine its weight of each index of elements. On such basis, countermeasure of improving e-commerce, such as establishing professional website for e-commerce of tourism enterprise, constructing information system of E-commerce of tourism enterprise and developing personalized service of tourism e-commerce, was put forward to raise the performance of e-commerce of tourism enterprise. [ABSTRACT FROM PUBLISHER]

In recent years, Android is widely used in cell phones. Dalvik is the virtual machine which is embedded inside the Android operating system, and executes the Android-based applications. Thus, improving efficiency of the Dalvik virtual machine plays an important role in optimizing performance of android-based mobile phones. In this paper, we present a comprehensive analysis of the Dalvik bytecodes and their frequency of use in common Android applications and use the results to determine the most frequently used bytecodes in Dalvik virtual machine to identify best targets for improvement. Our analysis showed that over 82% of total execution time of our Android benchmarks is spent by only 5 families of instructions. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel efficient dataflow execution method for mobile context monitoring applications. As a key approach to minimize the execution overhead, we propose a new dataflow execution model, producer-oriented model. Compared to the conventional consumer-oriented model adopted in stream processing engines, our model significantly reduces execution overhead to process context monitoring dataflow reflecting unique characteristics of context monitoring. To realize the model, we develop DataBank, an execution container that takes charge of the management and delivery of the output data for the associated operator. We demonstrate the effectiveness of DataBank by implementing three useful applications and their dataflow graphs, i.e., MusicMap, FindMyPhone, and CalorieMonitor. Using the applications, we show that DataBank reduces the CPU utilization by more than 50%, compared to the methods based on the consumer-oriented model; DataBank enables more context monitoring applications to run concurrently. [ABSTRACT FROM PUBLISHER]

As a process description language of Web service composition, WS-BPEL only describes the orchestration process of the Web service composition. And we need to optimize the system performance by proposing a formal model of the process to analyze performance of the composition. This paper presents to make use of Queueing Petri Nets [1–2] to formal modeling of BPEL processes, use simulation tool QPME[3–4] to imitate simulation service composition, finally analyze and verify one of the performance indicators: mean service response time, service utilization and mean token population by the quantitative analysis method. [ABSTRACT FROM PUBLISHER]

Main memory is expected to grow significantly in both speed and capacity for it is a major shared resource among cores in a multi-core system, which will lead to increasing power consumption. Therefore, it is critical to address the power issue without seriously decreasing performance in the memory subsystem. In this paper, we firstly propose memory affinity which retains the active and low power memory ranks as long as possible to avoid frequently switching between active and low power status, and then present a memory affinity aware scheduling (MAS) to balance performance, power, thermal and fairness for multi-core systems. Experimental results demonstrate our memory affinity aware scheduling algorithms well adapt to system loading to maximize power saving and avoid memory hotspot at the same time while sustaining the system bandwidth demand and preserving fairness among threads. [ABSTRACT FROM PUBLISHER]

This paper presents a model of a horizontal cloud federation and studies the optimal resource selection and allocation policy a service provider should put in place to scale the performance, availability and security guarantees offered to customers. The proposed model considers: (i) resources located in different zones, characterized by different hourly costs and specific performance, availability, and security properties, (ii) service provider customers, dispersed in various zones(characterized by different latencies), and demanding services with different QoS levels defined in Service Level Agreements(SLAs). From this model we define an optimization problem allowing to determine the optimal distribution of the incoming load and the proper allocation of outsourced resources that satisfies the SLAs and that minimizes the outsourcing costs, thus allowing the maximization of the SP revenue. Experiments show how the optimal policy scales the service provider capabilities when the workload grows 10 times and more. [ABSTRACT FROM PUBLISHER]

A central goal of cloud computing is high resource utilization through hardware sharing; however, utilization often remains modest in practice due to the challenges in predicting consolidated application performance accurately. We present a thorough experimental study of consolidated n-tier application performance at high utilization to address this issue through reproducible measurements. Our experimental method illustrates opportunities for increasing operational efficiency by making consolidated application performance more predictable in high utilization scenarios. The main focus of this paper are non-trivial dependencies between SLA-critical response time degradation effects and software configurations (i.e., readily available tuning knobs). Methodologically, we directly measure and analyze the resource utilizations, request rates, and performance of two consolidated n-tier application benchmark systems (RUBBoS) in an enterprise-level computer virtualization environment. We find that monotonically increasing the workload of an n-tier application system may unexpectedly spike the overall response time of another co-located system by 300 percent despite stable throughput. Based on these findings, we derive a software configuration best-practice to mitigate such non-monotonic response time variations by enabling higher request-processing concurrency (e.g., more threads) in all tiers. More generally, this experimental study increases our quantitative understanding of the challenges and opportunities in the widely used (but seldom supported, quantified, or even mentioned) hypothesis that applications consolidate with linear performance in cloud environments. [ABSTRACT FROM PUBLISHER]

A crucial challenge for scientific workflow management systems is to support the efficient and scalable storage and querying of large provenance datasets that record the history of in silico experiments. As new provenance management systems are being developed, it is important to have benchmarks that can evaluate these systems and provide an unbiased comparison. In this paper, based on the requirements for scientific workflow provenance systems, we design an extensible benchmark that features a collection of techniques and tools for workload generation, query selection, performance measurement, and experimental result interpretation. [ABSTRACT FROM PUBLISHER]

In network layer protocols, the most efficient way of sending similar packets to a group of nodes is via multicast. Multicast is a profound concept that has been around for some time and has seen through its implementation in various aspects of today's network access technology. The IEEE 802.11 wireless standards, however, loosely honor IP layer multicast packets by encapsulating them in broadcast frames. This in turn degrades the 802.11 network access bandwidth capacity and further decreases its data transmission reliability. An enhancement workaround which has been devised was to encapsulate multicast packets in a unicast MAC layer frame. In addition, RTP was also observed to be an enabler to better user experience in multicast streaming. In this paper, we investigate the 802.11g multicast performance with and without the enhanced multicast mechanism. We further expand our investigation by implementing RTP during the multimedia multicast stream and without it. Our results lead us to conclude that there are significant advantages of using both the enhanced multicast mechanism and RTP during a multicast streaming via the 802.11g wireless standard. [ABSTRACT FROM PUBLISHER]

Ad hoc On-demand Distance Vector (AODV) is one of reactive routing protocol in Mobile Ad hoc Network (MANET) and many variants are developed based on modifying this protocol. Purposes of modification were mostly related to security and performance improvement, yet the additional processes being introduced in the modification could incur overheads to the modified AODV. The purpose of this paper is to evaluate some of the modified AODV protocols performance by examining their effectiveness in alleviating the black hole attack and further examining the effect of mitigation methods used on overhead. The performance analysis focuses on two conditions, i.e. no-attack and under-attack. Three modified AODV protocols were studied, namely idsAODV, HDAODV and EAODV, and a new modified protocol is proposed. Using NS-2 network simulator, the performance of these protocols under no-attack and under-attack scenarios were collected and analyzed. Simulations were conducted by varying the pause times in random waypoint mobility model. The performance results are presented using comparative analysis based on different performance matrices such as throughput, Packet Delivery Ratio, End-to-end delay, Network Routing Load and Energy usage. The results show that the three modified AODV protocols give positive effect to network performance in both conditions — under-attack and no-attack environment. EAODV protocol outperforms other modified protocols with highest network performance, but with longer delay and higher energy usage than the other modified protocols. [ABSTRACT FROM PUBLISHER]

Implementations of state machine replication are prevalently using variants of Paxos or other leader-based protocols. Typically these protocols are also leader-centric, in the sense that the leader performs more work than the non-leader replicas. Such protocols scale poorly, because as the number of replicas or the load on the system increases, the leader replica quickly reaches the limits of one of its resources. In this paper we show that much of the work performed by the leader in a leader-centric protocol can in fact be evenly distributed among all the replicas, thereby leaving the leader only with minimal additional workload. This is done (i) by distributing the work of handling client communication among all replicas, (ii) by disseminating client requests among replicas in a distributed fashion, and (iii) by executing the ordering protocol on ids. We derive a variant of Paxos incorporating these ideas. Compared to leader-centric protocols, our protocol not only achieves significantly higher throughput for any given number of replicas, but also increases its throughput with the number of replicas. [ABSTRACT FROM PUBLISHER]

Network Coding has been proven to be a method that will increase the throughput of network. Network coding will perform an XOR operation in the intermediate nodes to improve the throughput of the network. The simulation of network coding in AODV to search for the route to destination will be conducted in MATLAB. This paper introduces the development of simulation to illustrate the performance of network coding in wireless ad hoc network. The simulation will calculate the transmit packet time according to the size of the packet. Lastly, average network throughput performance between AODV network without network coding and network with network coding is shown and compared. [ABSTRACT FROM PUBLISHER]

Near Field Communication (NFC) is one of the technologies, in conjunction with Bluetooth and 6LoWPAN, which makes feasible the wireless transmission of information from small objects and sensors to Internet-enabled devices. This presents a new technological generation, denominated Internet of Things (IoT), which is able to integrate in Internet the sensors and objects located surround us. Our research work is focused on the evaluation of the capabilities from the mentioned technologies for the integration of a continuous data transmission model. Specifically, this paper analyzes the capabilities for transmitting continuous data from NFC. This presents special considerations and constrains, since it was not originally designed for this purpose. Specifically, it has been considered, for this evaluation, a sensor with high requirements in data transmission, an electrocardiogram (ECG). Over this sensor is presented an evaluation of the performance with the native communication model from the sensor, i.e. sending via NFC all the collected data, concluding that it is necessary to perform data compression when the amount of data to send is too large, since this introduces a delay of 2 bytes for each 127 bytes. Therefore, this work also presents a solution of pre-processed and data compression to make feasible the communication with NFC technology. [ABSTRACT FROM PUBLISHER]

This paper complements our previous results in the context of effectively and efficient designing Parallel Relational Data Warehouses (PRDW) over heterogenous database clusters, which are represented by the proposal of a methodology called Fragmentation & Allocation (F& A). The main merit of F& A is that of combining the fragmentation and the allocation phases simultaneously, which are instead performed separately by traditional approaches. In this paper, we prove the practical impact and the reliability of F& A on a real-life parallel processing database system. [ABSTRACT FROM PUBLISHER]

There are dramatically increasing interests from both academic and industry in the trend of cloud computing. Cloud computing depends on the idea of computing on demand that provide, support and delivery of computing services with stable and large data space. Our research concerns with improving the searching process in the cloud storage via avoiding the bottleneck in central ontology cloud storage system since all data chunks in the cloud must be indexed by a master ontology server.The contribution of this paper proposes new cloud storage architecture based distributed ontology as one of the main semantic technologies. This architecture provides better scalability, fault tolerance and enhanced performance for searching in the cloud storage avoiding the central bottleneck [ABSTRACT FROM PUBLISHER]

The nature of operation of Thin Client computing makes their performance to be affected by both the quality of the network and the terminals. For the past few years, there are few analyses on the performance of Thin Clients that can produce reliable, valid, and up-to-date results collected in a well designed and evaluated experiment based research. This paper analyses the performance of Thin Clients through experiment based research. The approach is to use benchmark application which is designed specifically for measurement of desktop computers by inserting delays in the visual elements of such benchmark application. In this technique, packet's behavior is measured on the network as the application is executed from the server to a Thin Client. The analysis through measurements of the performance shows that the improvement of computer processing power has a lot of performance metrics and comparing the trend with the results collected nearly seven years ago by previous researchers. Moreover, the bandwidth is found to be the main bottleneck for the performance of Thin Clients while the CPU is of less concern. [ABSTRACT FROM PUBLISHER]

The reconfigurable processors like FPGA are extensively used for cryptographic applications which have reduced the time to market of the hardware logic. This paper describes the high performance pipelined hardware implementation of RC5 algorithm in Xilinx Vertex II Pro FPGA with a 12-stage pipeline scheme that has achieved an encryption rate of 6.9 Gbps. The proposed design operates on 12 input data and a common key where each clock signal produces a partial single round encryption output. After 12 clocks cycles, the cipher text of the corresponding input data is derived at the output sequentially for every clock transition. The pipelined hardware was implemented and the efficiency was compared with the other versions of RC5. [ABSTRACT FROM PUBLISHER]