Memory hierarchy and data communication in heterogeneous reconfigurable SoCs

The miniaturization race in the hardware industry aiming at continuous increasing of transistor density on a die does not bring respective application performance improvements any more. One of the most promising alternatives is to exploit a heterogeneous nature of common applications in hardware. Supported by reconfigurable computation, which has already proved its efficiency in accelerating data intensive applications, this concept promises a breakthrough in contemporary technology development. Memory organization in such heterogeneous reconfigurable architectures becomes very critical. Two primary aspects introduce a sophisticated trade-off. On the one hand, a memory subsystem should provide well organized distributed data structure and guarantee the required data bandwidth. On the other hand, it should hide the heterogeneous hardware structure from the end-user, in order to support feasible high-level programmability of the system. This thesis work explores the heterogeneous reconfigurable hardware architectures and presents possible solutions to cope the problem of memory organization and data structure. By the example of the MORPHEUS heterogeneous platform, the discussion follows the complete design cycle, starting from decision making and justification, until hardware realization. Particular emphasis is made on the methods to support high system performance, meet application requirements, and provide a user-friendly programmer interface. As a result, the research introduces a complete heterogeneous platform enhanced with a hierarchical memory organization, which copes with its task by means of separating computation from communication, providing reconfigurable engines with computation and configuration data, and unification of heterogeneous computational devices using local storage buffers. It is distinguished from the related solutions by distributed data-flow organization, specifically engineered mechanisms to operate with data on local domains, particular communication infrastructure based on Network-on-Chip, and thorough methods to prevent computation and communication stalls. In addition, a novel advanced technique to accelerate memory access was developed and implemented.

6G enabled IoV scenarios with distributed intelligence mechanisms

The Internet of Vehicles (IoV) paradigm has emerged in recent times, where with the support of technologies like the Internet of Things and V2X , Vehicular Users (VUs) can access different services through internet connectivity. With the support of 6G technology, the IoV paradigm will evolve further and converge into a fully connected and intelligent vehicular system. However, this brings new challenges over dynamic and resource-constrained vehicular systems, and advanced solutions are demanded. This dissertation analyzes the future 6G enabled IoV systems demands, corresponding challenges, and provides various solutions to address them. The vehicular services and application requests demands proper data processing solutions with the support of distributed computing environments such as Vehicular Edge Computing (VEC). While analyzing the performance of VEC systems it is important to take into account the limited resources, coverage, and vehicular mobility into account. Recently, Non terrestrial Networks (NTN) have gained huge popularity for boosting the coverage and capacity of terrestrial wireless networks. Integrating such NTN facilities into the terrestrial VEC system can address the above mentioned challenges. Additionally, such integrated Terrestrial and Non-terrestrial networks (T-NTN) can also be considered to provide advanced intelligent solutions with the support of the edge intelligence paradigm. In this dissertation, we proposed an edge computing-enabled joint T-NTN-based vehicular system architecture to serve VUs. Next, we analyze the terrestrial VEC systems performance for VUs data processing problems and propose solutions to improve the performance in terms of latency and energy costs. Next, we extend the scenario toward the joint T-NTN system and address the problem of distributed data processing through ML-based solutions. We also proposed advanced distributed learning frameworks with the support of a joint T-NTN framework with edge computing facilities. In the end, proper conclusive remarks and several future directions are provided for the proposed solutions.

Searching and retrieving in content-based repositories of formal mathematical knowledge

In this thesis, the author presents a query language for an RDF (Resource Description Framework) database and discusses its applications in the context of the HELM project (the Hypertextual Electronic Library of Mathematics). This language aims at meeting the main requirements coming from the RDF community. in particular it includes: a human readable textual syntax and a machine-processable XML (Extensible Markup Language) syntax both for queries and for query results, a rigorously exposed formal semantics, a graph-oriented RDF data access model capable of exploring an entire RDF graph (including both RDF Models and RDF Schemata), a full set of Boolean operators to compose the query constraints, fully customizable and highly structured query results having a 4-dimensional geometry, some constructions taken from ordinary programming languages that simplify the formulation of complex queries. The HELM project aims at integrating the modern tools for the automation of formal reasoning with the most recent electronic publishing technologies, in order create and maintain a hypertextual, distributed virtual library of formal mathematical knowledge. In the spirit of the Semantic Web, the documents of this library include RDF metadata describing their structure and content in a machine-understandable form. Using the author's query engine, HELM exploits this information to implement some functionalities allowing the interactive and automatic retrieval of documents on the basis of content-aware requests that take into account the mathematical nature of these documents.

How do Firms ask for Consumers’ Data Permission? The Value of Companies Data Practices.

On May 25, 2018, the EU introduced the General Data Protection Regulation (GDPR) that offers EU citizens a shelter for their personal information by requesting companies to explain how people’s information is used clearly. To comply with the new law, European and non-European companies interacting with EU citizens undertook a massive data re-permission-request campaign. However, if on the one side the EU Regulator was particularly specific in defining the conditions to get customers’ data access, on the other side, it did not specify how the communication between firms and consumers should be designed. This has left firms free to develop their re-permission emails as they liked, plausibly coupling the informative nature of these privacy-related communications with other persuasive techniques to maximize data disclosure. Consequently, we took advantage of this colossal wave of simultaneous requests to provide insights into two issues. Firstly, we investigate how companies across industries and countries chose to frame their requests. Secondly, we investigate which are the factors that influenced the selection of alternative re-permission formats. In order to achieve these goals, we examine the content of a sample of 1506 re-permission emails sent by 1396 firms worldwide, and we identify the dominant “themes” characterizing these emails. We then relate these themes to both the expected benefits firms may derive from data usage and the possible risks they may experience from not being completely compliant to the spirit of the law. Our results show that: (1) most firms enriched their re-permission messages with persuasive arguments aiming at increasing consumers’ likelihood of relinquishing their data; (2) the use of persuasion is the outcome of a difficult tradeoff between costs and benefits; (3) most companies acted in their self-interest and “gamed the system”. Our results have important implications for policymakers, managers, and customers of the online sector.

Machine learning as a service for high energy physics (MLaaS4HEP): a service for ML-based data analyses

With the CERN LHC program underway, there has been an acceleration of data growth in the High Energy Physics (HEP) field and the usage of Machine Learning (ML) in HEP will be critical during the HL-LHC program when the data that will be produced will reach the exascale. ML techniques have been successfully used in many areas of HEP nevertheless, the development of a ML project and its implementation for production use is a highly time-consuming task and requires specific skills. Complicating this scenario is the fact that HEP data is stored in ROOT data format, which is mostly unknown outside of the HEP community. The work presented in this thesis is focused on the development of a ML as a Service (MLaaS) solution for HEP, aiming to provide a cloud service that allows HEP users to run ML pipelines via HTTP calls. These pipelines are executed by using the MLaaS4HEP framework, which allows reading data, processing data, and training ML models directly using ROOT files of arbitrary size from local or distributed data sources. Such a solution provides HEP users non-expert in ML with a tool that allows them to apply ML techniques in their analyses in a streamlined manner. Over the years the MLaaS4HEP framework has been developed, validated, and tested and new features have been added. A first MLaaS solution has been developed by automatizing the deployment of a platform equipped with the MLaaS4HEP framework. Then, a service with APIs has been developed, so that a user after being authenticated and authorized can submit MLaaS4HEP workflows producing trained ML models ready for the inference phase. A working prototype of this service is currently running on a virtual machine of INFN-Cloud and is compliant to be added to the INFN Cloud portfolio of services.

Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

Opportunistic Data Gathering and Dissemination in Urban Scenarios

In the era of the Internet of Everything, a user with a handheld or wearable device equipped with sensing capability has become a producer as well as a consumer of information and services. The more powerful these devices get, the more likely it is that they will generate and share content locally, leading to the presence of distributed information sources and the diminishing role of centralized servers. As of current practice, we rely on infrastructure acting as an intermediary, providing access to the data. However, infrastructure-based connectivity might not always be available or the best alternative. Moreover, it is often the case where the data and the processes acting upon them are of local scopus. Answers to a query about a nearby object, an information source, a process, an experience, an ability, etc. could be answered locally without reliance on infrastructure-based platforms. The data might have temporal validity limited to or bounded to a geographical area and/or the social context where the user is immersed in. In this envisioned scenario users could interact locally without the need for a central authority, hence, the claim of an infrastructure-less, provider-less platform. The data is owned by the users and consulted locally as opposed to the current approach of making them available globally and stay on forever. From a technical viewpoint, this network resembles a Delay/Disruption Tolerant Network where consumers and producers might be spatially and temporally decoupled exchanging information with each other in an adhoc fashion. To this end, we propose some novel data gathering and dissemination strategies for use in urban-wide environments which do not rely on strict infrastructure mediation. While preserving the general aspects of our study and without loss of generality, we focus our attention toward practical applicative scenarios which help us capture the characteristics of opportunistic communication networks.

Decentralized systems for the protection and portability of personal data

The General Data Protection Regulation (GDPR) has been designed to help promote a view in favor of the interests of individuals instead of large corporations. However, there is the need of more dedicated technologies that can help companies comply with GDPR while enabling people to exercise their rights. We argue that such a dedicated solution must address two main issues: the need for more transparency towards individuals regarding the management of their personal information and their often hindered ability to access and make interoperable personal data in a way that the exercise of one's rights would result in straightforward. We aim to provide a system that helps to push personal data management towards the individual's control, i.e., a personal information management system (PIMS). By using distributed storage and decentralized computing networks to control online services, users' personal information could be shifted towards those directly concerned, i.e., the data subjects. The use of Distributed Ledger Technologies (DLTs) and Decentralized File Storage (DFS) as an implementation of decentralized systems is of paramount importance in this case. The structure of this dissertation follows an incremental approach to describing a set of decentralized systems and models that revolves around personal data and their subjects. Each chapter of this dissertation builds up the previous one and discusses the technical implementation of a system and its relation with the corresponding regulations. We refer to the EU regulatory framework, including GDPR, eIDAS, and Data Governance Act, to build our final system architecture's functional and non-functional drivers. In our PIMS design, personal data is kept in a Personal Data Space (PDS) consisting of encrypted personal data referring to the subject stored in a DFS. On top of that, a network of authorization servers acts as a data intermediary to provide access to potential data recipients through smart contracts.

Serverless middlewares to integrate heterogeneous and distributed services in cloud continuum environments

The application of modern ICT technologies is radically changing many fields pushing toward more open and dynamic value chains fostering the cooperation and integration of many connected partners, sensors, and devices. As a valuable example, the emerging Smart Tourism field derived from the application of ICT to Tourism so to create richer and more integrated experiences, making them more accessible and sustainable. From a technological viewpoint, a recurring challenge in these decentralized environments is the integration of heterogeneous services and data spanning multiple administrative domains, each possibly applying different security/privacy policies, device and process control mechanisms, service access, and provisioning schemes, etc. The distribution and heterogeneity of those sources exacerbate the complexity in the development of integrating solutions with consequent high effort and costs for partners seeking them. Taking a step towards addressing these issues, we propose APERTO, a decentralized and distributed architecture that aims at facilitating the blending of data and services. At its core, APERTO relies on APERTO FaaS, a Serverless platform allowing fast prototyping of the business logic, lowering the barrier of entry and development costs to newcomers, (zero) fine-grained scaling of resources servicing end-users, and reduced management overhead. APERTO FaaS infrastructure is based on asynchronous and transparent communications between the components of the architecture, allowing the development of optimized solutions that exploit the peculiarities of distributed and heterogeneous environments. In particular, APERTO addresses the provisioning of scalable and cost-efficient mechanisms targeting: i) function composition allowing the definition of complex workloads from simple, ready-to-use functions, enabling smarter management of complex tasks and improved multiplexing capabilities; ii) the creation of end-to-end differentiated QoS slices minimizing interfaces among application/service running on a shared infrastructure; i) an abstraction providing uniform and optimized access to heterogeneous data sources, iv) a decentralized approach for the verification of access rights to resources.