A Survey of Multistage Interconnection Networks

Background: Multistage interconnection networks are being used in computer and communications. Multiprocessor architectures for parallel computing exercise these interconnection networks for connecting various processing elements and transfer data between sub-systems of a digital system. The vast diversity of the field poses an obstacle to realize different kinds of interconnection networks and their relationship. Methods: This paper consists of an extensive survey of multistage interconnection networks. Results: A broad classification of multistage interconnection networks based on network functionality, reliability and fault tolerance is presented in order to emphasize the important principles which differentiate the network architectures. For each class of network, significant results are given and the basic design principles are explained. Conclusion: The various multistage interconnection networks design provide high performance, availability, throughput, lower latency, less power consumption along with improved fault-tolerance and reliability. However, there is a rising demand for new fault-tolerant and reliable multistage interconnection networks.

Beliefs propagation in log domain: a neural inspired algorithm for machine learning

In this paper, we consider a variant of belief propagation algorithm in a tree graphical model where computations are carried out in the negative log-likelihood domain. Unlike the min-product algorithm, our goal is not limited to estimating the mode of the marginal distribution. We would like to obtain the entire marginal distribution as the sum-product algorithm does. We applied the algorithm to learn effective users features for A/B testing. We discussed scalable extension to the proposed algorithm for processing large amount of data.The primary goal of a parallel program is to reduce running time comparing to the sequential program by taking full advantage of computing power of multiprocessors. Threads are widely used in the implementation of parallelism in shared memory multiprocessor architectures. For UNIX/LINUX systems, pthread is the POSIX standard threading interface, which provides support a standardized way for creating and synchronizing threads. Here we presents how pthreads can be used successfully in parallelizing real scientific problems. We will illustrate it by implementing the shared memory parallel version of Jacobi iteration algorithm. Results of performance tests showed that the speedups can be up to p where p is the number of processors.