SystemC:一种新的系统建模语言

文章介绍了一种国外正在研究的新的系统建模语言SystemC，因其较好地结合了面向对象的设计方法和硬件建模的特点，从而有望解决系统建模和HW／SW协同设计中等一系列问题。     

Algorithmic aspects for functional partitioning and scheduling in hardware/software co-design

Hardware/software (HW/SW) partitioning and scheduling are the crucial steps during HW/SW co-design. It has been shown that they are classical combinatorial optimization problems. Due to the possible sequential or concurrent execution of the tasks, HW/SW partitioning and scheduling has become more difficult to solve optimally. In this paper more efficient heuristic algorithms are proposed for the HW/SW partitioning and scheduling. The proposed algorithm partitions a task graph by iteratively moving the task with highest benefit-to-area ratio in higher priority. The benefit-to-area ratio is updated in each iteration step to cater for the task concurrence. The proposed algorithm for task scheduling executes the task lying in hardware-only critical path in higher priority to enhance the task forecast. A large body of experimental results conclusively shows that the proposed heuristic algorithm for partitioning is superior to the latest efficient combinatorial algorithm (Tabu search) cited in this paper. Moreover, the Tabu search for partitioning has been further improved by utilizing the proposed heuristic solution as its initial solution. In addition, the proposed scheduling algorithm obtains the improvements over the most widely used approaches by up to 10% without large increase in running time. This work was presented in part at 2006 IEEE International Conference on Field Programmable Technology (ICFPT).     

An interactive co-evolutionary CAD system for garment pattern design

Traditional CAD (Computer-Aided Design) methods in garment pattern design (GPD) fail to utilize the knowledge of experts for inexperienced designers. Moreover, the interactive and co-evolutionary features are not supported. We propose an interactive co-evolutionary CAD system for GPD (ICE-GCAD). The functionality model, modular architecture and data flow of the system are proposed. Then, the interactive co-evolutionary system whose core module is an immune-inspired co-evolutionary algorithm is studied. Finally, the flow of co-design in the system is proposed. As a case demonstration, we study a design sample of a leisure shirt. The experimental studies show that our approach has promising performance and appealing effects. We believe ICE-GCAD is applicable to support the collaboration among garment designers and experts.     

面向RTOS的嵌入式软件模拟器构造与实现方法

提出一种快速嵌入式软件验证工具——RTOS软件模拟器。在RTOS软件模拟器验证方法中,利用RTOS模块化、层次化设计特点,快速实现嵌入式软件在不同目标机器间的代码移植,通过扩展RTOS API功能,建立硬件模拟驱动,实现软件模拟器和硬件模拟器通信连接和协同模拟同步控制。RTOS软件模拟器克服ISS速度低的缺点,从更高层次验证嵌入式软件功能。     

Event-triggered fuzzy filtering in networked control system for a class of non-linear system with time delays

This paper focuses on the design of H _∞ filter and event-triggered scheme for a class of continuous non-linear networked control systems (NCSs) based on fuzzy system appeared with time delays. First, we consider the discrete event-triggered (ET) scheme to make efficient utilisation of bandwidth. Under this ET-scheme, sensor releases the data only when our sampled-data plant violates the specific event-triggered condition. Second, the T-S fuzzy system is used to model the non-linear NCSs. Another purpose of this paper is to design filters involving delays. Such filters have a more general form than the delay-free filters that have been mostly considered in the traditional studies. By using the time-delay system, co-design of event-triggered scheme and H _∞ filter for the delayed NCSs is presented in a unified frame work. To choose the latest data packet and discard the dis-ordered packet logic, zero-order hold is inserted between the fuzzy filter and event generator. Then, by using the novel fuzzy Lyapunov–Krasovskii function approach with free-weighting matrix technique, H _∞ filter design of event-triggered delay NCSs is proposed. Finally, to show the effective result of our co-design method, a tunnel-diode example is given.     

Particle swarm optimization applied to the co-design of a fuel cell air circuit

This paper presents an optimization approach applied to a whole fuel cell (FC) air supply system including its geometry and its control. The aim is to optimize its power consumption along with its mass. Particle swarm optimization (PSO) algorithm is used to define the design parameters of both permanent magnet synchronous motor (PMSM) and a fuzzy logic controller (FLC). The results are compared with those obtained by a sequential optimization process and advantages of co-design optimization approach are clearly shown. Indeed, a significant reduction of the objective function (made up on both motor mass and energy consumption) on a considered operating cycle can be obtained.     

Ontological reasoning in the design space exploration of advanced cyber–physical systems

Cyber–physical systems are becoming increasingly complex. In these advanced systems, the different engineering domains involved in the design process become more and more intertwined. Therefore, a traditional (sequential) design process becomes inefficient in finding good design options. Instead, an integrated approach is needed where parameters in multiple different engineering domains can be chosen, evaluated, and optimized to achieve a good overall solution. However, in such an approach, the combined design space becomes vast. As such, methods are needed to mitigate this problem.In this paper, we show a method for systematically capturing and updating domain knowledge in the context of a co-design process involving different engineering domains, i.e. control and embedded. We rely on ontologies to reason about the relationships between parameters in the different domains. This allows us to derive a stepwise design space exploration workflow where this domain knowledge is used to quickly reduce the design space to a subset of likely good candidates. We illustrate our approach by applying it to the design space exploration process for an advanced electric motor control system and its deployment on embedded hardware.     

QoS-oriented design of embedded systems with specification PEARL

Only recently have methodical tools adequate to design real-time systems been formally introduced in design methodologies. Naturally, they were present from the beginning, but due to the large diversity of embedded systems’ areas of deployment, specially dedicated formalisms have been developed and used. High-level language programming and integration of modeling formalisms into design methods eased the development of more complex real-time applications. With the emerging object-oriented programming languages and design methods, their integration into larger information systems has become more transparent. It was the UML methodology, however, which eventually merged also the design methods and concepts of real-time systems into a consistent whole. It took a large consortium and a long process to persuade industry of the benefits the new integral methodology can offer. On the other hand, there are some trade-offs, and there are some features not completely covered, yet. Here, a different, more straightforward approach to program and design (embedded) real-time systems is presented. Since it emerged from the real-time community, it includes most features relevant there. Independent of the UML profile for schedulability, performance and time specification, a profile was devised for use in PEARL-oriented UML design. The strengths of the mentioned language and design methods for QoS-oriented design of (embedded) real-time systems are emphasised throughout this article.