When a cloud user allocates a cluster to execute a map-reduce workload, the user must determine the number and type of virtual machine instances to minimize the workload's financial cost. The cloud user may rent on-demand instances at a fixed price or spot instances at a variable price to execute the workload. Although the cloud user may bid on spot virtual machine instances at a reduced rate, the spot market auction may delay the workload's start or terminate the spot instances before the workload completes. The cloud user requires a forecast for the workload's financial cost and completion time to analyze the trade-offs between on-demand and spot instances. While existing estimation tools predict map-reduce workloads' completion times and costs, these tools do not provide spot instance estimates because a spot market auction determines the instance's start time and duration. The ephemeral spot instances impact execution time estimates because the spot market auction forces the map-reduce workloads to use different storage strategies to persist data after the spot instances terminate. The spot market also reduces the existing tools' completion time and cost estimate accuracy because the tool must factor in spot instance wait times and early terminations. This dissertation updated an existing tool to forecast map-reduce workload's monetary cost and completion time based on spot market historical traces. The enhanced estimation tool includes three new enhancements over existing tools. First, the estimation tool models the impact to the execution from new storage strategies. Second, the enhanced tool calculates additional execution time from early spot instance termination. Finally, the enhance tool predicts the workloads wait time and early termination probabilities from historic traces. Based on two historical Amazon EC2 spot market traces, the enhancements reduce the average completion time prediction error by 96% and the average monetary cost prediction error by 99% over existing tools.

O tópico principal desta tese de doutorado foi a efficiência da braçada no nado crawl. A tese foi composta e dividida em três artigos originais, com o objetivo de: (1) investigar as relações existentes entre a eficiência da braçada e a potência de membros superiores na determinação da velocidade máxima do nado crawl, (2) estimar os efeitos da pernada na velocidade de nado e no cálculo da eficiência da braçada no nado crawl, e (3) comparar os diferentes métodos utilizados para estimativa da eficiência da braçada e identificar os principais preditores biofísicos da velocidade máxima em 200 m crawl utilizando apenas os braços. Diferentes métodos foram utilizados para quantificar a eficiência da braçada, como o modelo da “roda de pás” (estudos 1, 2, e 3), a razão entre a velocidade de nado e a velocidade deslocamento da mão (estudo 3), e o método utilizando o MAD System (estudo 3). A contribuição da pernada foi estimada individualmente, considerando as diferenças de velocidade de nado para uma determinada frequência gestual, em diferentes intensidades. Os componentes úteis e não-úteis para a potência mecânica total exercida pela braçada foram obtidos por meio de protocolos fora d’água (utilizando um ergômetro de brações específico; estudo 1) e dentro d’água (utilizando o MAD System; estudo 3), combinados com medidas fisiológicas e biomecânicas, incluindo a eficiência da braçada. A velocidade máxima em 200 m teve como determinantes o equilíbrio entre variáveis biomecânicas (75% das variâncias pôde ser explicado pela potência mecânica externa e a eficiência da braçada; 98% das variâncias pôde ser explicado pela potência mecânica externa, eficiência propulsiva e o coeficiente de arrasto) e variáveis fisiológicas (98% das variâncias pôde ser explicado pela potência metabólica total e o custo energético). Ainda, a contribuição da pernada para a velocidade de nado aumentou com o aumento da frequência de braçadas (e da velocidade). Assim, ajustes individuais relativamente à contribuição da pernada devem ser considerados no cálculo da eficiência da braçada ao se nadar o nado crawl “completo” (usando braços e pernas). Por fim, os diferentes métodos fornecem valores de eficiência significativamente diferentes, embora haja concordância entre os mesmos. Portanto, valores de eficiência da braçada devem ser interpretados com cautela, considerando o método utilizado. / The main topic of this thesis was the arm stroke efficiency in front crawl swimming. Hence, it was developed in three original articles aiming to: (1) investigate the interplay between propelling efficiency and arm’s power output in determining the maximal speed in front crawl swimming, (2) estimate the effects of leg kick on the swimming speed and on arm stroke efficiency in front crawl, and (3) to compare different methods to assess the arm stroke efficiency and to identify the main biophysical predictors of maximal speed in 200 m swimming with the arms only. Different approaches were used to quantify the arm stroke efficiency. For instance, the paddle-wheel model (studies 1, 2, and 3), the ratio forward speed/hand speed (study 3), and the MAD System approach (study 3). The leg kick contribution was estimated individually, considering the differences in speed at paired stroke frequencies, in a range of speeds. Useful and non-useful components of the total mechanical power exerted by the arm stroke were obtained from dry land (using a customized arm-crank ergometer; study 1) and swimming protocols (using the MAD System; study 3), combined to the assessment of physiological and biomechanical parameters, including the arm stroke efficiency. The maximal speed in 200 m was determined by the balance between biomechanical (75% of the variances explained by the external mechanical power and the arm stroke efficiency; 98% of the variances explained by the external mechanical power, the arm stroke efficiency and the speed-specific drag) and physiological parameters (98% of the variances explained by the total metabolic power and the energy cost of swimming). Moreover, leg kick contribution to forward speed increased from low to maximal stroke frequencies (and speeds) and individual adjustments to the leg kick contribution should be considered when assessing the arm stroke efficiency in “full front crawl stroke” front crawl. Furthermore, the different methods provided significantly different values of arm stroke efficiency, although they agreed with each other. Therefore, arm stroke efficiency data should be interpreted carefully, considering the method used.

The work presented in this thesis targets the analysis and implementation of multi-criteria performance prediction methods for System-on-Chips (SoC). These new SoC architectures offer the opportunity to integrate complete heterogeneous systems into a single chip and can be used to design battery powered handhelds, security critical systems, consumer electronics devices, etc. However, this variety in terms of application usually comes with a lot of different performance objectives like power consumption, yield, design cost, production cost, silicon area and many others. These performance requirements are often very difficult to meet together so that SoC design usually relies on making the right design choices and finding the best performance compromises. In parallel with this architectural paradigm shift, new Very Deep Submicron (VDSM) silicon processes have more and more impact on the performances and deeply modify the way a VLSI system is designed even at the first stages of a design flow. In such a context where many new technological and system related variables enter the game, early exploration of the impact of design choices becomes crucial to estimate the performance of the system to design and reduce its time-to-market. In this context, this thesis presents: - A study of state-of-the-art tools and methods used to estimate the performances of VLSI systems and an original classification based on several features and concepts that they use. Based on this comparison, we highlight their weaknesses and lacks to identify new opportunities in performance prediction. - The definition of new concepts to enable the automatic exploration of large design spaces based on flexible performance criteria and degrees of freedom representing design choices. - The implementation of a couple of two new tools of our own: - Nessie, a tool enabling hierarchical representation of an application along with its platform and automatically performs the mapping and the estimation of their performance. -Yeti, a C++ library enabling the defintion and value estimation of closed-formed expressions and table-based relations. It provides the user with input and model sensitivity analysis capability, simulation scripting, run-time building and automatic plotting of the results. Additionally, Yeti can work in standalone mode to provide the user with an independent framework for model estimation and analysis. To demonstrate the use and interest of these tools, we provide in this thesis several case studies whose results are discussed and compared with the literature. Using Yeti, we successfully reproduced the results of a model estimating multi-core computation power and extended them thanks to the representation flexibility of our tool. We also built several models from the ground up to help the dimensioning of interconnect links and clock frequency optimization. Thanks to Nessie, we were able to reproduce the NoC power consumption results of an H.264/AVC decoding application running on a multicore platform. These results were then extended to the case of a 3D die stacked architecture and the performance benets are then discussed. We end up by highlighting the advantages of our technique and discuss future opportunities for performance prediction tools to explore.

<p>As cloud computing is gaining popularity, many application owners are migrating their</p><p>applications into the cloud. However, because of the diversity of the cloud environments</p><p>and the complexity of the modern applications, it is very challenging to find out which</p><p>cloud environment is best fitted for one's application.</p><p>In this dissertation, we design and build systems to help application owners select the</p><p>most suitable cloud environments for their applications. The first part of this thesis focuses</p><p>on how to compare the general fitness of the cloud environments. We present CloudCmp,</p><p>a novel comparator of public cloud providers. CloudCmp measures the elastic computing,</p><p>persistent storage, and networking services offered by a cloud along metrics that directly</p><p>reflect their impact on the performance of customer applications. CloudCmp strives to</p><p>ensure fairness, representativeness, and compliance of these measurements while limiting</p><p>measurement cost. Applying CloudCmp to four cloud providers that together account</p><p>for most of the cloud customers today, we find that their offered services vary widely in</p><p>performance and costs, underscoring the need for thoughtful cloud environment selection.</p><p>From case studies on three representative cloud applications, we show that CloudCmp can</p><p>guide customers in selecting the best-performing provider for their applications.</p><p>The second part focuses on how to let customers compare cloud environments in the</p><p>context of their own applications. We describe CloudProphet, a novel system that can</p><p>accurately estimate an application's performance inside a candidate cloud environment</p><p>without the need of migration. CloudProphet generates highly portable shadow programs</p><p>to mimic the behavior of a real application, and deploys them inside the cloud to estimate</p><p>the application's performance. We use the trace-and-replay technique to automatically</p><p>generate high-fidelity shadows, and leverage the popular dispatcher-worker pattern</p><p>to accurately extract and enforce the inter-component dependencies. Our evaluation in</p><p>three popular cloud platforms shows that CloudProphet can help customers pick the bestperforming</p><p>cloud environment, and can also accurately estimate the performance of a</p><p>variety of applications.</p> / Dissertation

Gas turbine engines are conceptually designed using performance maps that describe the compressor’s effect on the cycle. During the traditional design process, the cycle designer selects a compressor design point based on criteria to meet cycle design point requirements, and performance maps are found or created for off-design analysis that meet this design point selection. Although the maps always have a pedigree to an existing compressor design, oftentimes these maps are scaled to account for design or technology changes. Scaling practices disconnect the maps from the geometry and flow associated with the reference compressor, or the design parameters which are needed for compressor preliminary design. A goal in gas turbine engine research is to bridge this disconnect in order to produce acceptable performance maps that are coupled with compressor design parameters. A new compressor conceptual design and performance prediction method has been developed which will couple performance maps to conceptual design parameters. This method will adapt and combine the key elements of compressor conceptual design with multiple-meanline analysis, allowing for a map of optimal performance that is attached to reasonable design parameters to be defined for cycle design. This method is prompted by the development of multi-fidelity (zooming) analysis capabilities, which allow compressor analysis to be incorporated into cycle analysis. Integrating compressor conceptual design and map generation into cycle analysis will allow for more realistic decisions to be made sooner, which will reduce the time and cost used for design iterations.

O tópico principal desta tese de doutorado foi a efficiência da braçada no nado crawl. A tese foi composta e dividida em três artigos originais, com o objetivo de: (1) investigar as relações existentes entre a eficiência da braçada e a potência de membros superiores na determinação da velocidade máxima do nado crawl, (2) estimar os efeitos da pernada na velocidade de nado e no cálculo da eficiência da braçada no nado crawl, e (3) comparar os diferentes métodos utilizados para estimativa da eficiência da braçada e identificar os principais preditores biofísicos da velocidade máxima em 200 m crawl utilizando apenas os braços. Diferentes métodos foram utilizados para quantificar a eficiência da braçada, como o modelo da “roda de pás” (estudos 1, 2, e 3), a razão entre a velocidade de nado e a velocidade deslocamento da mão (estudo 3), e o método utilizando o MAD System (estudo 3). A contribuição da pernada foi estimada individualmente, considerando as diferenças de velocidade de nado para uma determinada frequência gestual, em diferentes intensidades. Os componentes úteis e não-úteis para a potência mecânica total exercida pela braçada foram obtidos por meio de protocolos fora d’água (utilizando um ergômetro de brações específico; estudo 1) e dentro d’água (utilizando o MAD System; estudo 3), combinados com medidas fisiológicas e biomecânicas, incluindo a eficiência da braçada. A velocidade máxima em 200 m teve como determinantes o equilíbrio entre variáveis biomecânicas (75% das variâncias pôde ser explicado pela potência mecânica externa e a eficiência da braçada; 98% das variâncias pôde ser explicado pela potência mecânica externa, eficiência propulsiva e o coeficiente de arrasto) e variáveis fisiológicas (98% das variâncias pôde ser explicado pela potência metabólica total e o custo energético). Ainda, a contribuição da pernada para a velocidade de nado aumentou com o aumento da frequência de braçadas (e da velocidade). Assim, ajustes individuais relativamente à contribuição da pernada devem ser considerados no cálculo da eficiência da braçada ao se nadar o nado crawl “completo” (usando braços e pernas). Por fim, os diferentes métodos fornecem valores de eficiência significativamente diferentes, embora haja concordância entre os mesmos. Portanto, valores de eficiência da braçada devem ser interpretados com cautela, considerando o método utilizado. / The main topic of this thesis was the arm stroke efficiency in front crawl swimming. Hence, it was developed in three original articles aiming to: (1) investigate the interplay between propelling efficiency and arm’s power output in determining the maximal speed in front crawl swimming, (2) estimate the effects of leg kick on the swimming speed and on arm stroke efficiency in front crawl, and (3) to compare different methods to assess the arm stroke efficiency and to identify the main biophysical predictors of maximal speed in 200 m swimming with the arms only. Different approaches were used to quantify the arm stroke efficiency. For instance, the paddle-wheel model (studies 1, 2, and 3), the ratio forward speed/hand speed (study 3), and the MAD System approach (study 3). The leg kick contribution was estimated individually, considering the differences in speed at paired stroke frequencies, in a range of speeds. Useful and non-useful components of the total mechanical power exerted by the arm stroke were obtained from dry land (using a customized arm-crank ergometer; study 1) and swimming protocols (using the MAD System; study 3), combined to the assessment of physiological and biomechanical parameters, including the arm stroke efficiency. The maximal speed in 200 m was determined by the balance between biomechanical (75% of the variances explained by the external mechanical power and the arm stroke efficiency; 98% of the variances explained by the external mechanical power, the arm stroke efficiency and the speed-specific drag) and physiological parameters (98% of the variances explained by the total metabolic power and the energy cost of swimming). Moreover, leg kick contribution to forward speed increased from low to maximal stroke frequencies (and speeds) and individual adjustments to the leg kick contribution should be considered when assessing the arm stroke efficiency in “full front crawl stroke” front crawl. Furthermore, the different methods provided significantly different values of arm stroke efficiency, although they agreed with each other. Therefore, arm stroke efficiency data should be interpreted carefully, considering the method used.

O tópico principal desta tese de doutorado foi a efficiência da braçada no nado crawl. A tese foi composta e dividida em três artigos originais, com o objetivo de: (1) investigar as relações existentes entre a eficiência da braçada e a potência de membros superiores na determinação da velocidade máxima do nado crawl, (2) estimar os efeitos da pernada na velocidade de nado e no cálculo da eficiência da braçada no nado crawl, e (3) comparar os diferentes métodos utilizados para estimativa da eficiência da braçada e identificar os principais preditores biofísicos da velocidade máxima em 200 m crawl utilizando apenas os braços. Diferentes métodos foram utilizados para quantificar a eficiência da braçada, como o modelo da “roda de pás” (estudos 1, 2, e 3), a razão entre a velocidade de nado e a velocidade deslocamento da mão (estudo 3), e o método utilizando o MAD System (estudo 3). A contribuição da pernada foi estimada individualmente, considerando as diferenças de velocidade de nado para uma determinada frequência gestual, em diferentes intensidades. Os componentes úteis e não-úteis para a potência mecânica total exercida pela braçada foram obtidos por meio de protocolos fora d’água (utilizando um ergômetro de brações específico; estudo 1) e dentro d’água (utilizando o MAD System; estudo 3), combinados com medidas fisiológicas e biomecânicas, incluindo a eficiência da braçada. A velocidade máxima em 200 m teve como determinantes o equilíbrio entre variáveis biomecânicas (75% das variâncias pôde ser explicado pela potência mecânica externa e a eficiência da braçada; 98% das variâncias pôde ser explicado pela potência mecânica externa, eficiência propulsiva e o coeficiente de arrasto) e variáveis fisiológicas (98% das variâncias pôde ser explicado pela potência metabólica total e o custo energético). Ainda, a contribuição da pernada para a velocidade de nado aumentou com o aumento da frequência de braçadas (e da velocidade). Assim, ajustes individuais relativamente à contribuição da pernada devem ser considerados no cálculo da eficiência da braçada ao se nadar o nado crawl “completo” (usando braços e pernas). Por fim, os diferentes métodos fornecem valores de eficiência significativamente diferentes, embora haja concordância entre os mesmos. Portanto, valores de eficiência da braçada devem ser interpretados com cautela, considerando o método utilizado. / The main topic of this thesis was the arm stroke efficiency in front crawl swimming. Hence, it was developed in three original articles aiming to: (1) investigate the interplay between propelling efficiency and arm’s power output in determining the maximal speed in front crawl swimming, (2) estimate the effects of leg kick on the swimming speed and on arm stroke efficiency in front crawl, and (3) to compare different methods to assess the arm stroke efficiency and to identify the main biophysical predictors of maximal speed in 200 m swimming with the arms only. Different approaches were used to quantify the arm stroke efficiency. For instance, the paddle-wheel model (studies 1, 2, and 3), the ratio forward speed/hand speed (study 3), and the MAD System approach (study 3). The leg kick contribution was estimated individually, considering the differences in speed at paired stroke frequencies, in a range of speeds. Useful and non-useful components of the total mechanical power exerted by the arm stroke were obtained from dry land (using a customized arm-crank ergometer; study 1) and swimming protocols (using the MAD System; study 3), combined to the assessment of physiological and biomechanical parameters, including the arm stroke efficiency. The maximal speed in 200 m was determined by the balance between biomechanical (75% of the variances explained by the external mechanical power and the arm stroke efficiency; 98% of the variances explained by the external mechanical power, the arm stroke efficiency and the speed-specific drag) and physiological parameters (98% of the variances explained by the total metabolic power and the energy cost of swimming). Moreover, leg kick contribution to forward speed increased from low to maximal stroke frequencies (and speeds) and individual adjustments to the leg kick contribution should be considered when assessing the arm stroke efficiency in “full front crawl stroke” front crawl. Furthermore, the different methods provided significantly different values of arm stroke efficiency, although they agreed with each other. Therefore, arm stroke efficiency data should be interpreted carefully, considering the method used.

No description available.

No description available.

Modeling pavement deterioration and predicting the pavement performance is crucial for optimum pavement network management. Currently only a few models exist that incorporate the structural capacity of the pavements into deterioration modeling. This thesis develops pavement deterioration models that take into account, along with the age of the pavement, the pavement structural condition expressed in terms of the Modified Structural Index (MSI). The research found MSI to be a significant input parameter that affects the rate of deterioration of a pavement section by using the Akaike Information Criterion (AIC). The AIC method suggests that a model that includes the MSI is at least 10^21 times more likely to be closer to the true model than a model that does not include the MSI. The developed models display the average deterioration of pavement sections for specific ages and MSI values. Virginia Department of Transportation (VDOT) annually collects pavement condition data on road sections with various lengths. Due to the nature of data collection practices, many biased measurements or influential outliers exist in this data. Upon the investigation of data quality and characteristics, the models were built based on filtered and cleansed data. Following the regression models, an empirical Bayesian approach was employed to reduce the variance between observed and predicted conditions and to deliver a more accurate prediction model. / Master of Science