Embedded systems design and design methodologies

Research focus

The Peer review has evaluated this group as Excellent

Embedded systems consist of hardware, software and an environment, involving computations subject to physical constraints. They can be designed as single system-on-chip, distributed, pervasive and intelligent, characterized by sensorial abilities. This implies that the design of embedded systems requires a holistic approach that integrates essential paradigms from hardware to software design in a consistent manner. The typical architecture of these systems, although it may have many aspects in common with general purpose computing systems, in which one or more processors, of different nature, cooperate with dedicated hardware modules through an interconnection network, either on-chip or wireless, actually requires more specific optimizations in terms of trade-offs of cost/performance, flexibility, reliability and power consumption. Furthermore, time to market must be minimized. This research group derives historically from competences both in computer architectures and electronic design automation, with the addition of younger researchers with a background in software, telecommunication and automation domains. The main research focus of the period under consideration has been the study and research in methodologies to support and possibly automate the design of different classes of embedded systems: - multicore system-on-chip platforms based on different processor architectures; - reconfigurable platforms; - intelligent measurement systems; - passive and semi-passive RFId, active Wireless Sensor Networks and UWB systems. The research activities carried out during the 2003-2006 timeframe are mainly related to the following two reseach areas: 1. Design Methodologies The research has focused on the development of methodologies, tools and platforms to support the designers in optimally mapping applications onto system-on-chip (SoC) platforms equipped with RISC, superscalar or Very-Long-Instruction-Word (VLIW) processors, considering also multi-processor architectures. The methodologies, and related developed frameworks, face all levels of abstraction of the concurrent hardware/software design flow: - System-level modeling, specification and verification through simulation of hardware/software systems; - Methodologies for design space exploration and partitioning of system-level specifications based on static and dynamic metrics in order to identify the best hardware/software mapping and software tasks allocation on multiprocessor platforms. The metrics are tailored for optimization of performance, power consumption and/or reliability on a given type of platform; - Methodologies and tools for simulation and optimization of hardware, software and communication components, in particular Network-on-Chip (NoC), for multi-processor-based platforms taking into account performance, reliability and power consumption figures of merit; - Methodologies and tools for the design of dynamically reconfigurable systems on FPGA-based platforms. In the embedded systems design automation research area, achievements consist mainly in the definition of methodologies and supporting tools, usually either open-source or defined in the frame of international research cooperations with other academic institutions and industrial partners. 2. Computational Intelligence Measurements Systems Research on intelligent measurements systems has focused on - Analysis and synthesis of computational intelligence-based systems in adaptive environments. 105 - Computational intelligence technologies in instrumentation and measurement for intelligent manufacturing applications, homeland protection and personal safety. The research addresses the design of systems for detecting critical materials both through molecular analysis and X-ray inspection. As a recent research activity the group is also focusing on RFID and WSN issues, and in particular, RFId systems have been studied at application-level by addressing energy consumption aspects and their impact on performance (reading throughput, tag localisation, reading distance), leading also to the creation of a start-up company. Wireless sensor networks have been studied at different levels to cover critical research issues such as - Solar adaptive energy harvesting mechanisms, power modeling and low-power design, in particular with respect to node architectures and wireless communication protocols; - Auto-localization of the network nodes in indoor and outdoor environments (RSSI signal, GPS and UWB). At the application level we are working in two scenarios: monitoring the Australian reef barrier (end user: Queenland’s Government) and evaluation of the residual risk associated with rocks collapse and landslides (end user: Italian fire brigade (national level), Siemens, Italdata). Future work in the research of embedded system design is oriented toward the definition of frameworks for the exploration of the best architectural trade-offs for heterogeneous Multiprocessor System on Chip for different application domains as well as addressing non stationarity aspects, clock synchronisation and adaptive solutions for wireless sensor networks and RFId systems.

Departments

Dipartimento di Elettronica e Informazione (DEI)

Professors

Cesare Alippi (full professor)
Mariagiovanna Sami (full professor)
Donatella Sciuto (full professor)
Cristiana Bolchini (associate professor)
Fabrizio Ferrandi (associate professor)
William Fornaciari (associate professor)
Lorenzo Mezzalira (associate professor)
Fabio Salice (associate professor)
Cristina Silvano (associate professor)
Giovanni Agosta (assistant professor)
Carlo Brandolese (assistant professor)
Francesco Bruschi (assistant professor)