Heterogeneous multicore systems for signal processing

This thesis explores the capabilities of heterogeneous multi-core systems, based on multiple Graphics Processing Units (GPUs) in a standard desktop framework. Multi-GPU accelerated desk side computers are an appealing alternative to other high performance computing (HPC) systems: being composed of commodity hardware components fabricated in large quantities, their price-performance ratio is unparalleled in the world of high performance computing. Essentially bringing “supercomputing to the masses”, this opens up new possibilities for application fields where investing in HPC resources had been considered unfeasible before. One of these is the field of bioelectrical imaging, a class of medical imaging technologies that occupy a low-cost niche next to million-dollar systems like functional Magnetic Resonance Imaging (fMRI). In the scope of this work, several computational challenges encountered in bioelectrical imaging are tackled with this new kind of computing resource, striving to help these methods approach their true potential. Specifically, the following main contributions were made: Firstly, a novel dual-GPU implementation of parallel triangular matrix inversion (TMI) is presented, addressing an crucial kernel in computation of multi-mesh head models of encephalographic (EEG) source localization. This includes not only a highly efficient implementation of the routine itself achieving excellent speedups versus an optimized CPU implementation, but also a novel GPU-friendly compressed storage scheme for triangular matrices. Secondly, a scalable multi-GPU solver for non-hermitian linear systems was implemented. It is integrated into a simulation environment for electrical impedance tomography (EIT) that requires frequent solution of complex systems with millions of unknowns, a task that this solution can perform within seconds. In terms of computational throughput, it outperforms not only an highly optimized multi-CPU reference, but related GPU-based work as well. Finally, a GPU-accelerated graphical EEG real-time source localization software was implemented. Thanks to acceleration, it can meet real-time requirements in unpreceeded anatomical detail running more complex localization algorithms. Additionally, a novel implementation to extract anatomical priors from static Magnetic Resonance (MR) scansions has been included.

Heterogeneous Multi-core Architectures for High Performance Computing

This thesis deals with heterogeneous architectures in standard workstations. Heterogeneous architectures represent an appealing alternative to traditional supercomputers because they are based on commodity components fabricated in large quantities. Hence their price-performance ratio is unparalleled in the world of high performance computing (HPC). In particular, different aspects related to the performance and consumption of heterogeneous architectures have been explored. The thesis initially focuses on an efficient implementation of a parallel application, where the execution time is dominated by an high number of floating point instructions. Then the thesis touches the central problem of efficient management of power peaks in heterogeneous computing systems. Finally it discusses a memory-bounded problem, where the execution time is dominated by the memory latency. Specifically, the following main contributions have been carried out: A novel framework for the design and analysis of solar field for Central Receiver Systems (CRS) has been developed. The implementation based on desktop workstation equipped with multiple Graphics Processing Units (GPUs) is motivated by the need to have an accurate and fast simulation environment for studying mirror imperfection and non-planar geometries. Secondly, a power-aware scheduling algorithm on heterogeneous CPU-GPU architectures, based on an efficient distribution of the computing workload to the resources, has been realized. The scheduler manages the resources of several computing nodes with a view to reducing the peak power. The two main contributions of this work follow: the approach reduces the supply cost due to high peak power whilst having negligible impact on the parallelism of computational nodes. from another point of view the developed model allows designer to increase the number of cores without increasing the capacity of the power supply unit. Finally, an implementation for efficient graph exploration on reconfigurable architectures is presented. The purpose is to accelerate graph exploration, reducing the number of random memory accesses.

Quality of Service in Distributed Stream Processing for large scale Smart Pervasive Environments

The wide diffusion of cheap, small, and portable sensors integrated in an unprecedented large variety of devices and the availability of almost ubiquitous Internet connectivity make it possible to collect an unprecedented amount of real time information about the environment we live in. These data streams, if properly and timely analyzed, can be exploited to build new intelligent and pervasive services that have the potential of improving people's quality of life in a variety of cross concerning domains such as entertainment, health-care, or energy management. The large heterogeneity of application domains, however, calls for a middleware-level infrastructure that can effectively support their different quality requirements. In this thesis we study the challenges related to the provisioning of differentiated quality-of-service (QoS) during the processing of data streams produced in pervasive environments. We analyze the trade-offs between guaranteed quality, cost, and scalability in streams distribution and processing by surveying existing state-of-the-art solutions and identifying and exploring their weaknesses. We propose an original model for QoS-centric distributed stream processing in data centers and we present Quasit, its prototype implementation offering a scalable and extensible platform that can be used by researchers to implement and validate novel QoS-enforcement mechanisms. To support our study, we also explore an original class of weaker quality guarantees that can reduce costs when application semantics do not require strict quality enforcement. We validate the effectiveness of this idea in a practical use-case scenario that investigates partial fault-tolerance policies in stream processing by performing a large experimental study on the prototype of our novel LAAR dynamic replication technique. Our modeling, prototyping, and experimental work demonstrates that, by providing data distribution and processing middleware with application-level knowledge of the different quality requirements associated to different pervasive data flows, it is possible to improve system scalability while reducing costs.

Design and implementation of bioinformatics tools for large scale genome annotation

The continuous increase of genome sequencing projects produced a huge amount of data in the last 10 years: currently more than 600 prokaryotic and 80 eukaryotic genomes are fully sequenced and publically available. However the sole sequencing process of a genome is able to determine just raw nucleotide sequences. This is only the first step of the genome annotation process that will deal with the issue of assigning biological information to each sequence. The annotation process is done at each different level of the biological information processing mechanism, from DNA to protein, and cannot be accomplished only by in vitro analysis procedures resulting extremely expensive and time consuming when applied at a this large scale level. Thus, in silico methods need to be used to accomplish the task. The aim of this work was the implementation of predictive computational methods to allow a fast, reliable, and automated annotation of genomes and proteins starting from aminoacidic sequences. The first part of the work was focused on the implementation of a new machine learning based method for the prediction of the subcellular localization of soluble eukaryotic proteins. The method is called BaCelLo, and was developed in 2006. The main peculiarity of the method is to be independent from biases present in the training dataset, which causes the over‐prediction of the most represented examples in all the other available predictors developed so far. This important result was achieved by a modification, made by myself, to the standard Support Vector Machine (SVM) algorithm with the creation of the so called Balanced SVM. BaCelLo is able to predict the most important subcellular localizations in eukaryotic cells and three, kingdom‐specific, predictors were implemented. In two extensive comparisons, carried out in 2006 and 2008, BaCelLo reported to outperform all the currently available state‐of‐the‐art methods for this prediction task. BaCelLo was subsequently used to completely annotate 5 eukaryotic genomes, by integrating it in a pipeline of predictors developed at the Bologna Biocomputing group by Dr. Pier Luigi Martelli and Dr. Piero Fariselli. An online database, called eSLDB, was developed by integrating, for each aminoacidic sequence extracted from the genome, the predicted subcellular localization merged with experimental and similarity‐based annotations. In the second part of the work a new, machine learning based, method was implemented for the prediction of GPI‐anchored proteins. Basically the method is able to efficiently predict from the raw aminoacidic sequence both the presence of the GPI‐anchor (by means of an SVM), and the position in the sequence of the post‐translational modification event, the so called ω‐site (by means of an Hidden Markov Model (HMM)). The method is called GPIPE and reported to greatly enhance the prediction performances of GPI‐anchored proteins over all the previously developed methods. GPIPE was able to predict up to 88% of the experimentally annotated GPI‐anchored proteins by maintaining a rate of false positive prediction as low as 0.1%. GPIPE was used to completely annotate 81 eukaryotic genomes, and more than 15000 putative GPI‐anchored proteins were predicted, 561 of which are found in H. sapiens. In average 1% of a proteome is predicted as GPI‐anchored. A statistical analysis was performed onto the composition of the regions surrounding the ω‐site that allowed the definition of specific aminoacidic abundances in the different considered regions. Furthermore the hypothesis that compositional biases are present among the four major eukaryotic kingdoms, proposed in literature, was tested and rejected. All the developed predictors and databases are freely available at: BaCelLo http://gpcr.biocomp.unibo.it/bacello eSLDB http://gpcr.biocomp.unibo.it/esldb GPIPE http://gpcr.biocomp.unibo.it/gpipe

Imaging of crustal scatterers using multiple seismic arrays

Array seismology is an useful tool to perform a detailed investigation of the Earth’s interior. Seismic arrays by using the coherence properties of the wavefield are able to extract directivity information and to increase the ratio of the coherent signal amplitude relative to the amplitude of incoherent noise. The Double Beam Method (DBM), developed by Krüger et al. (1993, 1996), is one of the possible applications to perform a refined seismic investigation of the crust and mantle by using seismic arrays. The DBM is based on a combination of source and receiver arrays leading to a further improvement of the signal-to-noise ratio by reducing the error in the location of coherent phases. Previous DBM works have been performed for mantle and core/mantle resolution (Krüger et al., 1993; Scherbaum et al., 1997; Krüger et al., 2001). An implementation of the DBM has been presented at 2D large-scale (Italian data-set for Mw=9.3, Sumatra earthquake) and at 3D crustal-scale as proposed by Rietbrock & Scherbaum (1999), by applying the revised version of Source Scanning Algorithm (SSA; Kao & Shan, 2004). In the 2D application, the rupture front propagation in time has been computed. In 3D application, the study area (20x20x33 km3), the data-set and the source-receiver configurations are related to the KTB-1994 seismic experiment (Jost et al., 1998). We used 60 short-period seismic stations (200-Hz sampling rate, 1-Hz sensors) arranged in 9 small arrays deployed in 2 concentric rings about 1 km (A-arrays) and 5 km (B-array) radius. The coherence values of the scattering points have been computed in the crustal volume, for a finite time-window along all array stations given the hypothesized origin time and source location. The resulting images can be seen as a (relative) joint log-likelihood of any point in the subsurface that have contributed to the full set of observed seismograms.

Global scale investigation of cirrus clouds properties using active and passive sensors

A year of satellite-borne lidar CALIOP data is analyzed and statistics on occurrence and distribution of bulk properties of cirri are provided. The relationship between environmental and cloud physical parameters and the shape of the backscatter profile (BSP) is investigated. It is found that CALIOP BSP is mainly affected by cloud geometrical thickness while only minor impacts can be attributed to other quantities such as optical depth or temperature. To fit mean BSPs as functions of geometrical thickness and position within the cloud layer, polynomial functions are provided. It is demonstrated that, under realistic hypotheses, the mean BSP is linearly proportional to the IWC profile. The IWC parameterization is included into the RT-RET retrieval algorithm, that is exploited to analyze infrared radiance measurements in presence of cirrus clouds during the ECOWAR field campaign. Retrieved microphysical and optical properties of the observed cloud are used as input parameters in a forward RT simulation run over the 100-1100 cm-1 spectral interval and compared with interferometric data to test the ability of the current single scattering properties database of ice crystal to reproduce realistic optical features. Finally a global scale investigation of cirrus clouds is performed by developing a collocation algorithm that exploits satellite data from multiple sensors (AIRS, CALIOP, MODIS). The resulting data set is utilized to test a new infrared hyperspectral retrieval algorithm. Retrieval products are compared to data and in particular the cloud top height (CTH) product is considered for this purpose. A better agreement of the retrieval with the CALIOP CTH than MODIS is found, even if some cases of underestimation and overestimation are observed.

Advanced modelling of time domain electromagnetic data with updated hydrogeological interpretations

Several countries have acquired, over the past decades, large amounts of area covering Airborne Electromagnetic data. Contribution of airborne geophysics has dramatically increased for both groundwater resource mapping and management proving how those systems are appropriate for large-scale and efficient groundwater surveying. We start with processing and inversion of two AEM dataset from two different systems collected over the Spiritwood Valley Aquifer area, Manitoba, Canada respectively, the AeroTEM III (commissioned by the Geological Survey of Canada in 2010) and the “Full waveform VTEM” dataset, collected and tested over the same survey area, during the fall 2011. We demonstrate that in the presence of multiple datasets, either AEM and ground data, due processing, inversion, post-processing, data integration and data calibration is the proper approach capable of providing reliable and consistent resistivity models. Our approach can be of interest to many end users, ranging from Geological Surveys, Universities to Private Companies, which are often proprietary of large geophysical databases to be interpreted for geological and\or hydrogeological purposes. In this study we deeply investigate the role of integration of several complimentary types of geophysical data collected over the same survey area. We show that data integration can improve inversions, reduce ambiguity and deliver high resolution results. We further attempt to use the final, most reliable output resistivity models as a solid basis for building a knowledge-driven 3D geological voxel-based model. A voxel approach allows a quantitative understanding of the hydrogeological setting of the area, and it can be further used to estimate the aquifers volumes (i.e. potential amount of groundwater resources) as well as hydrogeological flow model prediction. In addition, we investigated the impact of an AEM dataset towards hydrogeological mapping and 3D hydrogeological modeling, comparing it to having only a ground based TEM dataset and\or to having only boreholes data.