Flávio Rech Wagner

Time and energy efficient mapping of embedded applications onto NoCs

This work analyzes the mapping of applications onto generic regular networks-on-chip (NoCs). Cores must be placed considering communication requirements, so as to minimize the overall application execution time and energy consumption. We expand previous mapping strategies by taking into consideration the dynamic behavior of the target application and thus potential contentions in the intercommunication of the cores. Experimental results for a suite of 22 benchmarks and various NoC sizes show that a 42% average reduction in the execution time of the mapped application can be obtained, together with a 21% average reduction in the total energy consumption for state-of-the-art technologies.

UAV relay network to support WSN connectivity

An important problem in Wireless Sensor Networks (WSN) is the occurrence of failures that lead to the disconnection of parts of the network, compromising the final results achieved by the WSN operation. A way to overcome such problem is to provide a reliable connection to support the connectivity via other types of nodes that communicate with the sensor nodes. This paper proposes the usage of a network composed by Unmanned Aerial Vehicles (UAVs) as a relay network to guarantee the delivery of data produced by WSN nodes on the ground to the users. Results from simulations of the proposed technique are provided and discussed.

CACO-PS: a general purpose cycle-accurate configurable power simulator

This paper presents a cycle-accurate and configurable simulator that estimates the power consumed by an embedded system. The simulator accepts as input a structural system architecture description, at a level of abstraction that can be configured by the user. The simulator has been used to study the power dissipation of different micro-architectures of a Java microcontroller while executing several applications. Thanks to the cycle-driven behavior and the structural system description, the simulator is both flexible and accurate, and it may also be fast, depending on the desired level of abstraction. It represents a valuable support in a design space exploration methodology, allowing a power consumption evaluation that can be applied to any processor and system architecture at an early design stage.

An Aspect-Oriented Approach for Dealing with Non-Functional Requirements in a Model-Driven Development of Distributed Embedded Real-Time Systems

This work presents a proposal to use aspect orientation in the analysis and design of distributed embedded real-time systems (DERTS). These systems have several requirements directly related to their main characteristics, the so-called non-functional requirements (NFR), which refer to orthogonal properties, conditions, and restrictions that are spread out over the entire system. Pure object-oriented methods do not address successfully those so called cross-cutting concerns, so new technologies, like aspect orientation, are applied in order to fulfill this gap. The paper presents DERAF istributed embedded real-time aspects framework, an extensible and high-level framework (i.e. implementation-independent) to handle NFR of DERTS at earlier design stages. DERAF combines the use of aspects with RT-UML, aiming to separate the handling of non-functional from functional requirements in the model driven design of DERTS. The paper presents the use of DERAF on a case study of an unmanned air vehicle (UAV)

Dynamic task allocation strategies in MPSoC for soft real-time applications

This work evaluates task allocation strategies based on bin-packing algorithms in the context of multiprocessor systems-on-chip (MPSoCs) with task migration capabilities, running soft real-time applications. The task migration model assumes that the whole code and data of the tasks are transferred from an origin node to the chosen destination node. We combine two types of algorithms to obtain better allocation results. Experimental results show that there is a trade-off between deadline misses and system energy consumption when applying bin-packing and linear clustering algorithms. In order to save energy, our system turns off idle processors and applies Dynamic Voltage Scaling to processors with slack. Depending on the algorithm selection and on the application, it is possible to obtain a reduction on deadline misses from 30 % to 100 % and energy consumption savings from 60 % to 80 %.

DERAF: a high-level aspects framework for distributed embedded real-time systems design

Distributed Embedded Real-time Systems (DERTS) have several requirements directly related to characteristics that are difficult to handle when a pure object-oriented method is used for their development. These requirements are called Non-Functional Requirements (NFR) and refer to orthogonal properties, conditions, and restrictions that are spread out over the system. Pure object-oriented methods do not address successfully those concerns, so new technologies, like aspect orientation, are being applied in order to fulfill this gap. This work presents a proposal to use aspect orientation in the analysis and design of DERTS. To support our proposal, we created DERAF (Distributed Embedded Real-time Aspects Framework), an extensible high-level framework (i.e. implementation-independent) to handle NFR of DERTS. DERAF is used together with RT-UML in the design phase, aiming to separate the handling of non-functional from functional requirements in the Model Driven Design of DERTS. A qualitative assessment of DERAF separation of concerns is also presented.

Evaluation of coordination strategies for heterogeneous sensor networks aiming at surveillance applications

A new challenge in the sensor network area is the coordination of heterogeneous sensors (with different sensing, mobility and computing capabilities) in an integrated network. This kind of sensor networks have clearly high relevance in surveillance systems, in which both low-end static ground sensor nodes and more sophisticated sensors carried by mobile platforms, such as unmanned aerial vehicles (UAVs), cooperate. This paper provides an analysis of two different strategies to guide the collaboration among the sensor nodes mentioned above, applied to area surveillance systems. The first analyzed problem is related to the choice of the UAV instance that will respond to a given alarm issued by a ground sensor node. The second issue is the estimation of the response time until any UAV can be engaged in handling an alarm and effectively handles it. Two strategies are introduced and compared: one based on a pheromone inspired approach and another based on utility functions inspired on risk profiles that models decisions of investors in the stock market.

Software Quality Metrics and their Impact on Embedded Software

Although many improvements for software development are proposed by software engineers, the embedded system community faces a hard task in applying these improvements to software development, due to the strong dependence between software and hardware in embedded systems, which raises a trade-off between software quality, measured by traditional metrics, and optimization for a specific platform. Traditional software quality concerns reuse, abstraction, coupling, and coherence. Such concepts are usually in conflict with performance, memory footprint, and other physical metrics used for design evaluation in embedded systems. The purpose of this work is to evaluate the relationship between quality metrics for software products and physical metrics for embedded systems, in order to guide an embedded designer in selecting the best alternative design during design space exploration already at the model level. After the experiments, we could analyze the correlation between these metrics and highlight the behavior for quality and physical metrics, which help us to better understand the trade-off between reuse and optimization.

Model driven engineering for MPSOC design space exploration

This paper presents a Model Driven Engineering approach for MPSoC Design Space Exploration (DSE) to deal with the ever-growing challenge of designing complex embedded systems. This approach allows the designer to automatically select the most adequate modeling solution for application, platform, and mapping between application and platform, in an integrated and simultaneous way and at a very early design stage, before system synthesis and code generation have been performed. The exploration is based on high-level estimates of physical characteristics of each candidate solution. In an experimental setting, the DSE tool automatically performs four design activities: it selects the number of processors, maps tasks to processors, allocates processors to bus segments, and sets the voltage of each processor. Experimental results, extracted from a DSE scenario for a real application, show that the proposed estimation and exploration approach may find a suitable solution regarding the design requirements and constraints in a very short time, with an acceptable accuracy, without relying on costly synthesis-and-simulation cycles.

Impact of task migration in NoC-based MPSoCs for soft real-time applications

This work analyzes the impact of task migration in the context of multiprocessor systems-on-chip, where processors are interconnected by a network-on-chip (NoC) and the system must adapt itself to a dynamic workload, such that performance and real-time constraints are met and energy consumption is minimized. The task migration model assumes that the whole code and data of the tasks are transferred from an origin node to the chosen destination node. Experimental results show that, even with a higher overhead than other possible approaches, task migration may be applied in NoC-based architectures, since it pays off the costs involved in the transfer in terms of overall system performance and energy consumption and may help to improve the fulfillment of task deadlines in soft real-time systems.