International Symposium on Shared Memory Multiprocessing, 1991 20 Fault-Tolerant Design for Multistage Routing Networks Andr e DeHon, Thomas Knight Jr., and Henry Minsky As the size of digital systems increases, the average length of time between single component failures diminishes. To avoid component related failures, large computers must be fault-tolerant; that is, the computer must perform ...

Interconnection networks are an important and well-studied topic in parallel computing and architecture, but a homogeneous and general method for defining and classifying the topologies and behaviors of interconnection networks is lacking. Topologies are usually specified informally by picture or more formally by permutations of wire enumerations. This paper presents an improved method for spec...

We may presume the neural networks are simplified models of the biological neurons system. The Artificial Neural Network (ANN) is an information processing system which is inspired by brain learning system. It is assumed that brain is composed of a large number of highly interconnected processing elements working in groups to solve specific problems. Various networks and algorithms have been pr...

multistage interconnection network. Various traffic control schemes have been proposed to handle hot-spot traffic [4–7, 17, 19, 24]. Among these schemes, the combining network [5, 6, 17], which can combine requests within a switching element accessing the same memory location, is an effective scheme for handling hot-spot traffic. It not only reduces network traffic, but also provides a fast syn...

We may presume the neural networks are simplified models of the biological neurons system. The Artificial Neural Network (ANN) is an information processing system which is inspired by brain learning system. It is assumed that brain is composed of a large number of highly interconnected processing elements working in groups to solve specific problems. Various networks and algorithms have been pr...

Mobile communication is nowadays taken for granted. Having started primarily as a service for speech communication, data service and mobile Internet access are now driving the evolution of network infrastructure. Operators are facing the challenge to match the demand by continuously expanding and upgrading the network infrastructure. However, the evolution of the customer’s demand is uncertain....

Simple Serial Synchronized (SSS) Multistage Interconnection Network (MIN) is a novel MIN architecture for connecting processors and memory modules in multiprocessors. Synchronized bit-serial communication simplifies the structure/control, and also solves the pin-limitation problem. The simple structure allows the use of a high frequency clock rate and a high throughput 3-dimensional multistage ...

ÐIn this paper, we present an algorithm for performing permutations of messages on multistage interconnection networks. Permutations of messages are needed in many parallel algorithms. The proposed algorithm is feasible for any networks that can connect each input to each output using a set of N nonblocking connections, where N is the number of ports on the network. Messages are segmented into ...

Rearrangeable multistage interconnection networks such as the Benes network realize any permutation, yet their routing algorithms are not cost-effective. On the other hand, non-rearrangeable networks can have inexpensive routing algorithms, but no simple technique exists to characterix all the permutations realized on these netwarks. This paper introduces the concept of frame and shows how iit ...

Feedforward neural network models are created for prediction of daily heating energy consumption of a NTNU university campus Gløshaugen using actual measured data for training and testing. Improvement of prediction accuracy is proposed by using neural network ensemble. Previously trained feed-forward neural networks are first separated into clusters, using k-means algorithm, and then the best n...