Multi-GPU support on the marrow algorithmic skeleton framework

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Government bond yield spreads in EMU countries: The story of an ephemeral convergence

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Economics from the NOVA – School of Business and Economics

Heterogeneous computing with an algorithmic skeleton framework

The Graphics Processing Unit (GPU) is present in almost every modern day personal computer. Despite its specific purpose design, they have been increasingly used for general computations with very good results. Hence, there is a growing effort from the community to seamlessly integrate this kind of devices in everyday computing. However, to fully exploit the potential of a system comprising GPUs and CPUs, these devices should be presented to the programmer as a single platform. The efficient combination of the power of CPU and GPU devices is highly dependent on each device’s characteristics, resulting in platform specific applications that cannot be ported to different systems. Also, the most efficient work balance among devices is highly dependable on the computations to be performed and respective data sizes. In this work, we propose a solution for heterogeneous environments based on the abstraction level provided by algorithmic skeletons. Our goal is to take full advantage of the power of all CPU and GPU devices present in a system, without the need for different kernel implementations nor explicit work-distribution.To that end, we extended Marrow, an algorithmic skeleton framework for multi-GPUs, to support CPU computations and efficiently balance the work-load between devices. Our approach is based on an offline training execution that identifies the ideal work balance and platform configurations for a given application and input data size. The evaluation of this work shows that the combination of CPU and GPU devices can significantly boost the performance of our benchmarks in the tested environments, when compared to GPU-only executions.

Towards an algorithmic skeleton framework for programming the Intel R Xeon PhiTM processor

The Intel R Xeon PhiTM is the first processor based on Intel’s MIC (Many Integrated Cores) architecture. It is a co-processor specially tailored for data-parallel computations, whose basic architectural design is similar to the ones of GPUs (Graphics Processing Units), leveraging the use of many integrated low computational cores to perform parallel computations. The main novelty of the MIC architecture, relatively to GPUs, is its compatibility with the Intel x86 architecture. This enables the use of many of the tools commonly available for the parallel programming of x86-based architectures, which may lead to a smaller learning curve. However, programming the Xeon Phi still entails aspects intrinsic to accelerator-based computing, in general, and to the MIC architecture, in particular. In this thesis we advocate the use of algorithmic skeletons for programming the Xeon Phi. Algorithmic skeletons abstract the complexity inherent to parallel programming, hiding details such as resource management, parallel decomposition, inter-execution flow communication, thus removing these concerns from the programmer’s mind. In this context, the goal of the thesis is to lay the foundations for the development of a simple but powerful and efficient skeleton framework for the programming of the Xeon Phi processor. For this purpose we build upon Marrow, an existing framework for the orchestration of OpenCLTM computations in multi-GPU and CPU environments. We extend Marrow to execute both OpenCL and C++ parallel computations on the Xeon Phi. We evaluate the newly developed framework, several well-known benchmarks, like Saxpy and N-Body, will be used to compare, not only its performance to the existing framework when executing on the co-processor, but also to assess the performance on the Xeon Phi versus a multi-GPU environment.

Potential M&A between TIM Brazil and Oi S.A: The irreversible force of Telecommunications convergence

The intrinsic forces of market aiming for telecom industry convergence has arrived to Brazil. This case presents real characters, a sequence of events and other public information that has been impacting two corporations studied in this case. TIM Brazil and Oi S.A, two top players in the Brazilian telecom industry mobile and fixed segment respectively. While a merge between the two of them looks perfect and simple in an operational perspective due to its vertical complementarity, bring to them opportunities to win over a bundle offer (multi service package) that will consolidate their market predominance. Macroeconomic and internal corporate contrasts between these companies’ environment might signal that an impulsive could have a high price to pay in the future.

Real convergence in per capita output and growth in Eurozone: A time-series approach

The real convergence hypothesis has spurred a myriad of empirical tests and approaches in the economic literature. This Work Project intends to test for real output and growth convergence in all N(N-1)/2 possible pairs of output and output growth gaps of 14 Eurozone countries. This paper follows a time-series approach, as it tests for the presence of unit roots and persistence changes in the above mentioned pairs of output gaps, as well as for the existence of growth convergence with autoregressive models. Overall, significantly greater evidence has been found to support growth convergence rather than output convergence in our sample.

An algorithmic approach to estimating the minimal number of periodic points for smooth self-maps of simply-connected manifolds

For a given self-map f of M, a closed smooth connected and simply-connected manifold of dimension m ≥ 4, we provide an algorithm for estimating the values of the topological invariant Dm r [f], which equals the minimal number of r-periodic points in the smooth homotopy class of f. Our results are based on the combinatorial scheme for computing Dm r [f] introduced by G. Graff and J. Jezierski [J. Fixed Point Theory Appl. 13 (2013), 63–84]. An open-source implementation of the algorithm programmed in C++ is publicly available at http://www.pawelpilarczyk.com/combtop/.

Algorithmic assistance to the optimization process in vehicle routing problems

Magdeburg, Univ., Fak. für Maschinenbau, Diss., 2013

On convergence of the maximum likelihood estimator in adaptive designs

Otto-von-Guericke-Universität Magdeburg, Fakultät für Mathematik, Dissertation, 2016

Convergence and morphological constraint in frogs : variation in postcranial morphology ; a contribution in celebration of the distinguished scholarship of Robert F. Inger on the occasion of his sixty-fifth birthday / Sharon B. Emerson.

n.s. no.43(1988)

Convergence across countries and regions: theory and empirics

This paper surveys the recent literature on convergence across countries and regions. I discuss the main convergence and divergence mechanisms identified in the literature and develop a simple model that illustrates their implications for income dynamics. I then review the existing empirical evidence and discuss its theoretical implications. Early optimism concerning the ability of a human capital-augmented neoclassical model to explain productivity differences across economies has been questioned on the basis of more recent contributions that make use of panel data techniques and obtain theoretically implausible results. Some recent research in this area tries to reconcile these findings with sensible theoretical models by exploring the role of alternative convergence mechanisms and the possible shortcomings of panel data techniques for convergence analysis.

Gerogescu-Roegen versus Solow/Stiglitz and the convergence to the Cobb-Douglas

The value of the elasticity of substitution of capital for resources is a crucial element in the debate over whether continual growth is possible. It is generally held that the elasticity has to be at least one to permit continual growth and that there is no way of estimating this outside the range of the data. This paper presents a model in which the elasticity is determined endogenously and may converge to one. It is concluded that the general opinion is wrong: that the possibility of continual growth does not depend on the exogenously given value of the elasticity and that the value of the elasticity outside the range of the data can be studied by econometric methods.

Convergence of the mass-transport steepest descent scheme for the sub-critical Patlak-Keller-Segel model

Variational steepest descent approximation schemes for the modified Patlak-Keller-Segel equation with a logarithmic interaction kernel in any dimension are considered. We prove the convergence of the suitably interpolated in time implicit Euler scheme, defined in terms of the Euclidean Wasserstein distance, associated to this equation for sub-critical masses. As a consequence, we recover the recent result about the global in time existence of weak-solutions to the modified Patlak-Keller-Segel equation for the logarithmic interaction kernel in any dimension in the sub-critical case. Moreover, we show how this method performs numerically in one dimension. In this particular case, this numerical scheme corresponds to a standard implicit Euler method for the pseudo-inverse of the cumulative distribution function. We demonstrate its capabilities to reproduce easily without the need of mesh-refinement the blow-up of solutions for super-critical masses.

Convergence of singular integrals with general measures

We show that L2-bounded singular integrals in metric spaces with respect to general measures and kernels converge weakly. This implies a kind of average convergence almost everywhere. For measures with zero density we prove the almost everywhere existence of principal values.