Energy consumption of parallel algorithms for solving linear systems on HPC architecture

Modern High-Performance Computing HPC systems are gradually increasing in size and complexity due to the correspondent demand of larger simulations requiring more complicated tasks and higher accuracy. However, as side effects of the Dennard’s scaling approaching its ultimate power limit, the efficiency of software plays also an important role in increasing the overall performance of a computation. Tools to measure application performance in these increasingly complex environments provide insights into the intricate ways in which software and hardware interact. The monitoring of the power consumption in order to save energy is possible through processors interfaces like Intel Running Average Power Limit RAPL. Given the low level of these interfaces, they are often paired with an application-level tool like Performance Application Programming Interface PAPI. Since several problems in many heterogeneous fields can be represented as a complex linear system, an optimized and scalable linear system solver algorithm can decrease significantly the time spent to compute its resolution. One of the most widely used algorithms deployed for the resolution of large simulation is the Gaussian Elimination, which has its most popular implementation for HPC systems in the Scalable Linear Algebra PACKage ScaLAPACK library. However, another relevant algorithm, which is increasing in popularity in the academic field, is the Inhibition Method. This thesis compares the energy consumption of the Inhibition Method and Gaussian Elimination from ScaLAPACK to profile their execution during the resolution of linear systems above the HPC architecture offered by CINECA. Moreover, it also collates the energy and power values for different ranks, nodes, and sockets configurations. The monitoring tools employed to track the energy consumption of these algorithms are PAPI and RAPL, that will be integrated with the parallel execution of the algorithms managed with the Message Passing Interface MPI.

Implementation of network entropy algorithms on hpc machines, with application to high-dimensional experimental data

Network Theory is a prolific and lively field, especially when it approaches Biology. New concepts from this theory find application in areas where extensive datasets are already available for analysis, without the need to invest money to collect them. The only tools that are necessary to accomplish an analysis are easily accessible: a computing machine and a good algorithm. As these two tools progress, thanks to technology advancement and human efforts, wider and wider datasets can be analysed. The aim of this paper is twofold. Firstly, to provide an overview of one of these concepts, which originates at the meeting point between Network Theory and Statistical Mechanics: the entropy of a network ensemble. This quantity has been described from different angles in the literature. Our approach tries to be a synthesis of the different points of view. The second part of the work is devoted to presenting a parallel algorithm that can evaluate this quantity over an extensive dataset. Eventually, the algorithm will also be used to analyse high-throughput data coming from biology.

Optimal pose selection for the calibration of an overconstrained Cable-Driven Parallel Robot

In this project an optimal pose selection method for the calibration of an overconstrained Cable-Driven Parallel robot is presented. This manipulator belongs to a subcategory of parallel robots, where the classic rigid "legs" are replaced by cables. Cables are flexible elements that bring advantages and disadvantages to the robot modeling. For this reason, there are many open research issues, and the calibration of geometric parameters is one of them. The identification of the geometry of a robot, in particular, is usually called Kinematic Calibration. Many methods have been proposed in the past years for the solution of the latter problem. Although these methods are based on calibration using different kinematic models, when the robot’s geometry becomes more complex, their robustness and reliability decrease. This fact makes the selection of the calibration poses more complicated. The position and the orientation of the endeffector in the workspace become important in terms of selection. Thus, in general, it is necessary to evaluate the robustness of the chosen calibration method, by means, for example, of a parameter such as the observability index. In fact, it is known from the theory, that the maximization of the above mentioned index identifies the best choice of calibration poses, and consequently, using this pose set may improve the calibration process. The objective of this thesis is to analyze optimization algorithms which aim to calculate an optimal choice of poses both in quantitative and qualitative terms. Quantitatively, because it is of fundamental importance to understand how many poses are needed. Not necessarily a greater number of poses leads to a better result. Qualitatively, because it is useful to understand if the selected combination of poses actually gives additional information in the process of the identification of the parameters.