A generalized version of the well known periodic Riccati differential equation, which arises in certain optimal filtering problems for linear periodic systems, is studied. A monotonicity property for symmetry periodic...
详细信息
A generalized version of the well known periodic Riccati differential equation, which arises in certain optimal filtering problems for linear periodic systems, is studied. A monotonicity property for symmetry periodic equilibrium solutions and the existence of a maximal symmetric periodic equilibrium solution are established.< >
The authors present a parallel algorithm for logic simulation of VLSI circuits. It is implemented on a network of transputers connected in a ring topology. The approach is based on partitioning a functionality matrix ...
详细信息
The authors present a parallel algorithm for logic simulation of VLSI circuits. It is implemented on a network of transputers connected in a ring topology. The approach is based on partitioning a functionality matrix representation of the circuit among the transputers and adopting a data flow technique for the solution. A significant aspect of the algorithm is that it overlaps computation with communication, thereby reducing the communication overhead. It also attempts even distribution of load in order to reduce processor idle time. The algorithm possesses the advantages of ease of implementation and ease of extension to incorporate additional parameters for simulation. Performance results of the algorithm are given.< >
With ever-increasing reliance on digital computers in embedded systems such as in space, avionics, manufacturing, and life-support monitoring/control applications, the need for dependable systems that deliver services...
详细信息
With ever-increasing reliance on digital computers in embedded systems such as in space, avionics, manufacturing, and life-support monitoring/control applications, the need for dependable systems that deliver services in a timely manner has become crucial. Embedded systems often interact with the external environment and operate under strict timeliness and reliability requirements. Fault tolerance and real-time requirements on a system often influence one another in subtle ways, for example, the requirements on a highly—available system, such as an air traffic control system, may derive the timing constraints imposed on certain critical tasks. In cases where a set of interacting tasks operate under strict timing constraints, missing a deadline may result in a catastrophic system failure, which was termed a dynamic failure in (Shin, Krishna, and Lee, 1985). This paper argues that fault- tolerance and real-time requirements are not orthogonal and it addresses some of the challenges that confront the designers of fault-tolerant real-time systems. These challenges include formal specification of reliability and timing requirements, appropriate language and operating system support for providing fault-tolerance in a time-critical system, new scheduling theories which consider multiple resources and fault-tolerance, tradeoff between time and space redundancy, and predictable redundancy management in the presence of faults.
Traditional scan design techniques such as level-sensitive scan design, scan path, and random-access scan suffer from the drawback that the extra test application effort (which includes both time and memory) required ...
详细信息
Traditional scan design techniques such as level-sensitive scan design, scan path, and random-access scan suffer from the drawback that the extra test application effort (which includes both time and memory) required is directly proportional to the number of latches and can become quite significant. A scan design technique termed partial parallel scan which reduces test application effort by one to two orders of magnitude is presented. Theoretical and practical aspects of the design method are discussed. The practical use of the partial parallel scan technique has been demonstrated with an LSI circuit and a VLSI circuit designed using silicon compiler tools.< >
This paper discusses and analyzes two load sharing (LS) issues: adjusting preferred lists and implementing a fault-tolerant mechanism in the presence of node failures. In an early paper, we have proposed to order the ...
详细信息
The problem of selecting routes for interprocess communication in a network with virtual cut-through capability, while balancing the network load and minimizing the number of times that a message gets buffered, is add...
详细信息
The problem of selecting routes for interprocess communication in a network with virtual cut-through capability, while balancing the network load and minimizing the number of times that a message gets buffered, is addressed. The approach taken is to formulate the route selection problem as a minimization problem, with a link cost function that depends on the traffic through the link. The form of this cost function is derived on the basis of the probability of establishing a virtual cut-through route. It is shown that this route selection problem is NP-hard, and so an approximate algorithm that tries to reduce the cost incrementally by rerouting traffic is developed. The performance of this algorithm is evaluated for two popular network topologies: the hypercube and the C-wrapped hexagonal mesh.< >
The issue of I/O device access in HARTS (Hexagonal Architecture for Real-Time Systems)-a distributed real-time computer system under construction at the University of Michigan-is explicitly addressed. Several candidat...
详细信息
The issue of I/O device access in HARTS (Hexagonal Architecture for Real-Time Systems)-a distributed real-time computer system under construction at the University of Michigan-is explicitly addressed. Several candidate solutions are introduced, explored and evaluated according to cost, complexity, reliability, and performance: (1) 'node-direct' distribution with the intranode bus and a local I/O bus; (2) use of dedicated I/O nodes, which are placed in the hexagonal mesh as regular applications nodes, but which provide I/O services rather than computing services; and (3) use of a separate I/O network; which has led to the proposal of an 'interlaced' I/O network. The interlaced I/O network is intended to provide both high performance without burdening node processors with I/O overhead and a high degree of reliability. Both static and dynamic multiownership protocols are developed for managing I/O device access in this I/O network. The relative merits of the two protocols are explored, and the performance and accessibility which each provides are simulated.< >
The probability of a station/node failing to deliver packets before their deadlines, called the probability of dynamic failure, P/sub dyn/, and the in -bounded delivery time, which is defined as the time period betwee...
详细信息
The probability of a station/node failing to deliver packets before their deadlines, called the probability of dynamic failure, P/sub dyn/, and the in -bounded delivery time, which is defined as the time period between the arrival of a packet and its delivery with probability greater than 1- in , are important performance parameters for the communication subsystems of a distributed real-time system. The parameters are derived and are used to evaluate the token passing protocol, the token ring scheduling protocol, and the P/sub i/-persistent protocol and a priority-based variation thereof. The communication subsystem equipped with different contention protocols as embedded Markov chains is modeled. The probability distributions of the access delay are then derived, from which P/sub dyn/ and T/sub in / can be calculated. Using P/sub dyn/ and I/sub in / as indices, the performances of these contention protocols are evaluated and compared over a wide range of traffic.< >
A method of partitioning a workspace using rectilinear visibility in 3-D or higher space is presented. Unlike the case of 2-D space, where the space of a partition is a rectangle, the shape of a partition in 3-D or hi...
详细信息
A method of partitioning a workspace using rectilinear visibility in 3-D or higher space is presented. Unlike the case of 2-D space, where the space of a partition is a rectangle, the shape of a partition in 3-D or higher space is arbitrary. In spite of the arbitrary shape of partitioned regions, it is proved that there exist dominance relations between regions. This relation is then utilized to solve efficiently the shortest path planning problem in 3-D or higher space.< >
暂无评论