A5089092418- Distributed and Parallel Computing Systems
- Parallel Computing and Optimization Techniques
- Cloud Computing and Resource Management
- Advanced Data Storage Technologies
- Scientific Computing and Data Management
- Distributed systems and fault tolerance
- Privacy-Preserving Technologies in Data
- Advanced Software Engineering Methodologies
- Service-Oriented Architecture and Web Services
- Interconnection Networks and Systems
- Algorithms and Data Compression
- Gene expression and cancer classification
- Embedded Systems Design Techniques
- Bioinformatics and Genomic Networks
- Gene Regulatory Network Analysis
- Stochastic Gradient Optimization Techniques
- COVID-19 diagnosis using AI
- Genomics and Chromatin Dynamics
- Artificial Intelligence in Healthcare and Education
- Advanced Database Systems and Queries
- Software System Performance and Reliability
- Genomics and Phylogenetic Studies
- Graph Theory and Algorithms
- Machine Learning in Healthcare
- IoT and Edge/Fog Computing
University of Turin
2015-2024
Consorzio Interuniversitario Nazionale per l'Informatica
2024
National Research Council
2003-2024
University of Turku
2015
Turku Centre for Computer Science
2015
Åbo Akademi University
2015
University of Stirling
2014
University of Pisa
2001-2009
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
2003-2006
Hungarian Academy of Sciences
2004
Workflows are among the most commonly used tools in a variety of execution environments. Many them target specific environment; few make it possible to execute an entire workflow different environments, e.g. Kubernetes and batch clusters. We present novel approach execution, called StreamFlow, that complements graph with declarative description potentially complex makes onto multiple sites not sharing common data space. StreamFlow is then exemplified on bioinformatics pipeline for...
Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated (FL) has been emerging as a method for privacy-preserving pooling of datasets employing collaborative training institutions by iteratively globally aggregating locally trained models. One critical performance challenge FL is operating on not independently and identically distributed (non-IID) among the federation participants. Even though this fragility...
Autonomic management can be used to improve the QoS provided by parallel/distributed applications. We discuss behavioural skeletons introduced in earlier work: rather than relying on programmer ability design "from scratch" efficient autonomic policies, we encapsulate general controller features into algorithmic skeletons. Then leave duty of specifying parameters needed specialise needs particular application at hand. This results having fast prototype and tune distributed/parallel...
The Open Computing Cluster for Advanced data Manipulation (OCCAM) is a multipurpose flexible HPC cluster designed and operated by collaboration between the University of Torino Sezione di Istituto Nazionale Fisica Nucleare. It aimed at providing flexible, reconfigurable extendable infrastructure to cater wide range different scientific computing use cases, including ones from solid-state chemistry, high-energy physics, computer science, big analytics, computational biology, genomics many...
In April 2018, under the auspices of POR-FESR 2014-2020 program Italian Piedmont Region, Turin's Centre on High-Performance Computing for Artificial Intelligence (HPC4AI) was funded with a capital investment 4.5M€ and it began its deployment. HPC4AI aims to facilitate scientific research engineering in areas Big Data Analytics. will specifically focus methods on-demand provisioning AI BDA Cloud services regional national industrial community, which includes large ecosystem Small-Medium...
The growing number of next-generation applications offers a relevant opportunity for healthcare services, generating an urgent need architectures systems integration. Moreover, the huge amount stored information related to events can be explored by adopting process-oriented perspective. This paper discusses Ambient Assisted Living architecture manage hospital home-care services. proposed solution relies on event manager integrate sources ranging from personal devices web-based applications....
Federated Learning (FL) is becoming popular in different industrial sectors where data access critical for security, privacy and the economic value of itself. Unlike traditional machine learning, all must be globally gathered analysis, FL makes it possible to extract knowledge from distributed across organizations that can coupled with Machine paradigms. In this work, we replicate, using Learning, analysis a pooled dataset (with AdaBoost) has been used define PRAISE score, which today among...
Abstract The computing capacity needed to process the data generated in modern scientific experiments is approaching ExaFLOPs. Currently, achieving such performances only feasible through GPU-accelerated supercomputers. Different languages were developed program GPUs at different levels of abstraction. Typically, more abstract languages, portable they are across GPUs. However, less and co-designed with hardware, room for code optimization and, eventually, performance. In HPC context,...
Programming models based on algorithmic skeletons promise to raise the level of abstraction perceived by programmers when implementing parallel applications, while guaranteeing good performance figures. At same time, however, they restrict freedom implement arbitrary parallelism exploitation patterns. In fact, efficiency is achieved restricting patterns provided programmer useful ones for which efficient implementations, as well and compositions, are known. this work we introduce muskel ,...
Shared memory multiprocessors have returned to popularity thanks rapid spreading of commodity multi-core architectures. However, little attention has been paid supporting effective streaming applications on these In this paper we describe FastFlow, a low-level programming framework based lock-free queues explicitly designed support high-level languages for applications. We compare FastFlow with state-of-the-art frameworks such as Cilk, OpenMP, and Intel TBB. experimentally demonstrate that...
Federated Learning has been proposed to develop better AI systems without compromising the privacy of final users and legitimate interests private companies. Initially deployed by Google predict text input on mobile devices, FL in many other industries. Since its introduction, mainly exploited inner working neural networks gradient descent-based algorithms either exchanging weights model or gradients computed during learning. While this approach very successful, it rules out applying...