scispace - formally typeset
Search or ask a question

Showing papers on "Multistage interconnection networks published in 2015"


Journal ArticleDOI
TL;DR: Analytical results demonstrate that the Pars network outperforms known regular networks, namely ABN, ASEN, EGN, and IEGN in terms of cost, fault-tolerance, terminal reliability, mean time to failure, and permutation capability.

52 citations


Journal ArticleDOI
TL;DR: Reliability analyses show that the use of multiple parallel Benes networks can obtain more advantages than other methods for Benes network, and this approach improves the Bene network to be used in large-scale systems in various aspects of reliability namely time-independent terminal reliability, time- independent broadcast reliability,time-dependent Terminal reliability, and time-dependent broadcast reliability.

36 citations


Journal ArticleDOI
TL;DR: A new implementation of crossbar network named scalable cross bar network (SCN) that is a non-blocking network is presented to cope with the aforementioned scaling problems and performance analysis results show that SCN outperforms multistage crossbar networks and multistages interconnection networks in terms of terminal reliability, mean time to failure, and system failure rate.
Abstract: Interconnection networks (INs) are used in wide applications of multi-processor systems in order to set up connections between various nodes such as processors and memory modules. However, there is a fundamental problem in INs that has always been considered as one of the most challenging issues in this area. Blocking problem in these networks degrades network performance and consequently the performance of the whole system. In the meantime, the main option for dealing with this problem is the use of non-blocking crossbar networks. However, there are engineering and scaling difficulties when using these networks in large-scale systems. The number of pins on a VLSI chip cannot exceed a few hundreds, which restricts the size of the largest crossbar that should be integrated into a single VLSI chip. Using the idea of multistage implementation of crossbar network can resolve the problem. However, the next problem that arises with this idea is high hardware cost. Therefore, in this paper, a new implementation of crossbar network named scalable crossbar network (SCN) that is a non-blocking network is presented to cope with the aforementioned scaling problems. In addition, performance analysis results show that SCN outperforms multistage crossbar networks and multistage interconnection networks in terms of terminal reliability, mean time to failure, and system failure rate.

22 citations


Journal ArticleDOI
TL;DR: This paper comprehensively analyzes all perspectives of the reliability (terminal, broadcast, and network reliability); all reliability equations are calculated for different network sizes.

19 citations


Journal ArticleDOI
TL;DR: Comparisons prove that the new gamma minus networks has better reliability performance than gamma networks, as it has shortest path from source to destination, so it possess less delay with disjoint minimum path set availability which has not been possessed by gamma network.

14 citations


Book ChapterDOI
01 Jan 2015
TL;DR: An depth study of reliability evaluation in multistage interconnection network, which includes terminal reliability of regular network known as shuffle exchange network and gamma network is studied.
Abstract: Multistage interconnection network provide communication among processors, memory modules and other devices in parallel computer systems. These networks are designed to provide fast and efficient communication with a reasonable cost. The number of stages, interconnection topology, and network configuration differentiate the reliability of each network. Reliability is used to measure the system capability to transform information from input to output devices and its depends on the reliability of its component. Evaluation of reliability of interconnection network has been attempted by researchers in the past. This paper is an depth study of reliability evaluation in multistage interconnection network. The measurement includes terminal reliability of regular network known as shuffle exchange network and gamma network.

7 citations


Journal ArticleDOI
TL;DR: The results marked nearly 50% reduction in the number of passes and proved improvement of scheduling in the Low Stage Interconnection Networks by GreedyZero algorithms.

4 citations


Proceedings ArticleDOI
12 Jun 2015
TL;DR: Terminal reliability of purposed network has been computed and demonstrated that it not only outperforms other SEN variants in terms of terminal reliability and cost but has the improved features of fault tolerance and disjoint minimal length path set.
Abstract: Multistage Interconnection Networks (MIN), characterized by minimum latency, high Bandwidth & Throughput and cost effectiveness as compared to counterparts, embedded in parallel and multiprocessing systems allow faster communication of data related to nuclear reactor and nuclear fusion in effective and efficient generation of electricity along with decision making and functioning of the system. Reliability and Fault Tolerance of different variants of SEN MIN such as SEN, SEN+, SEN+2 exist in literature. Recently reliability evaluation of SEN-has been advanced. Limitations such as no full connectivity, Single path availability have been figured out by us and also (i) a new topology of SEN-has been purposed that mitigates the limitations, and (ii) Terminal reliability of purposed network has been computed and demonstrated that it not only outperforms other SEN variants in terms of terminal reliability and cost but has the improved features of fault tolerance and disjoint minimal length path set.

4 citations


01 Jan 2015
TL;DR: A variety of fault tolerant multistage interconnection networks that have been proposed in literature are surveyed and are capable of handling requests even in presence of faults although at reduced performance.
Abstract: In this paper variety of fault tolerant multistage interconnection networks that have been proposed in literature are surveyed .Fault tolerant networks are capable of handling requests even in presence of faults although at reduced performance. Various networks which we have surveyed include Augmented Baseline Network (ABN) , Irregular Augmented Baseline Network (IABN), Modified Augmented Baseline Network (MABN), Augmented Shuffle Exchange Network (ASEN-2), Irregular Augmented Shuffle Exchange Network (IASEN), Irregular Augmented Shuffle Network (IASN),Improved Irregular Augmented Shuffle Network(IIASN), New Irregular Augmented Shuffle Network( NIASN), Modified Augmented Shuffle Exchange Network (MASEN), Irregular Augmented Shuffle Exchange Network–3 (IASEN-3), Modified Alpha Network (MALN), Advance Irregular Alpha Multistage Interconnection Network (AIAMIN2), Irregular Advance Omega Network (IAON).

4 citations


Proceedings ArticleDOI
01 Sep 2015
TL;DR: A method Link-Switch Conflicts (LSC) is proposed on Optical Omega Networks, which detects Link Conflicts and switch conflicts separately and is used to minimize the crosstalk problem.
Abstract: Multistage Interconnection Network (MIN) is a class of high-speed network and formed by many stages of interconnected switches. With the growth of parallel processing, the MIN has become a hotspot of this field. Optical Multistage Interconnection networks (OMINs) came into existence because of its high speed of data transmission as compare to electrical (traditional) MIN. OMINs are high speed interconnection networks but also have some issues like crosstalk. Crosstalk problem is generated by undesired coupling of two wavelengths. These undesired coupling could be caused by Link conflicts and Switch Conflicts. In Electronic MINs there is only Link conflicts but in Optical MINs both Switch Conflicts and Link Conflicts occurs. Based on study and analysis a number of researches have been done for resolving these conflicts. In this paper, we have proposed a method Link-Switch Conflicts (LSC) on Optical Omega Networks, which detects Link Conflicts and switch conflicts separately. We are also routing these conflicted messages to resolve crosstalk. The results of Link-Switch Conflict (LSC) method are analyzed and compared with Windows Method (WM), Improved Windows Method (IWM) in Omega Network. This method is used to minimize the crosstalk problem.

3 citations


Journal ArticleDOI
TL;DR: The reliability equations on MLMINs are formulated to achieve two objectives: development of analytical methods using reliability equations to present an exact solution for computing the reliability of ML MINs, and preparing a basis for calculating the optimal values for topological parameters ofMLMINs in terms of reliability.
Abstract: A non-negligible demand on today's modern interconnection networks is to deliver multicast traffic. One of the new ideas to cope with this problem is to use the multilayer multistage interconnection networks (MLMINs). On the other hand, another critical parameter to prove the performance of most systems is reliability. Therefore, in this paper, our focus is to formulate the reliability equations on MLMINs to achieve two objectives: First, development of analytical methods using reliability equations to present an exact solution for computing the reliability of MLMINs, second, preparing a basis for calculating the optimal values for topological parameters of MLMINs ($$G_\mathrm{S}, G_\mathrm{F}$$GS,GF, and $$G_\mathrm{L}$$GL) in terms of reliability.

Proceedings ArticleDOI
01 Sep 2015
TL;DR: Performance in terms of probability of acceptance improves for MASEN as compared to MALPHA for larger network sizes, though at somewhat higher cost, whereas, on the reliability front MalPHA shows better results than the MASEN Network.
Abstract: Multistage Interconnection Networks (MINs) play an important role in the performance of a multiprocessor system and provide optimum tradeoff between performance and cost. Many irregular MINs have been proposed in recent times, owing to their multipath and cost efficient features in comparison to regular ones. In this paper, performance and reliability of Modified Augmented Shuffle Exchange Network (MASEN) and Modified Alpha (M-ALPHA) network has been evaluated for varying network sizes (16×16 to 1024×1024). Reliability models and expressions have been derived under upper and lower bound assumptions. Performance in terms of probability of acceptance improves for MASEN as compared to MALPHA for larger network sizes, though at somewhat higher cost, whereas, on the reliability front MALPHA shows better results than the MASEN Network.

Journal ArticleDOI
TL;DR: The idea of flattening is generalized to all Delta networks, in addition to some non-Delta ones such as Benes and Clos, and used data mining in order to reach a unified and meaningful performance parameter.

Journal ArticleDOI
TL;DR: The proposed method for the performance analysis of multistage interconnection networks (MINs) supports modelling and analysis of switch fabrics built on such switching networks based on the idea of a generalized traffic source outlined in the paper.
Abstract: A new method for the performance analysis of multistage interconnection networks (MINs) is presented. It supports modelling and analysis of switch fabrics built on such switching networks. The method is based on the idea of a generalized traffic source outlined in the paper. Using the generalized traffic idea, the new method overcomes the problems and limitations encountered in existing MIN performance analysis methods and can capture a larger variety of switching networks. Application of the proposed method and its generalizability are discussed. A higher flexibility of this new method to consider diverse traffic patterns is also reported. Sample results of the analysis proposed in this contribution are compared with the results of earlier methods and found superior. Simulation validation is also provided. The method is simple yet powerful enough to help designers to find the optimal structure of switching network for building a scalable router.

Proceedings ArticleDOI
01 May 2015
TL;DR: This algorithm can be used to minimize the cross talk problem of high speed OMINs and is proposed on Omega Networks for detecting Link Conflicts and switch conflicts.
Abstract: Multistage Interconnection Networks (MINs) are most competent high-speed interconnection networks (INs) which are form by many stages of interconnected switches. Multistage Interconnection Networks (MINs) is the most emerging technology, which is used, in broadband switching and multiprocessor systems. With the rapid expansion of high performance computing system, the MIN performance has become a key factor of controlling the overall performance. Due to some limitations of MINs, high-speed Optical Multistage Interconnection networks (OMINs) came into existence to improve the performance. Cross talk problem is the most vital issue of high speed OMINs, which is form by undesired coupling of two wavelengths. Link conflicts and Switch Conflicts can cause cross talk. If anyone or both conflicts appear in MIN then the cross talk problem arises. In traditional MINs, only Link conflicts occur but in Optical MINs, both conflicts occur. In this paper, we have proposed Link-Switch Conflict (LSC) algorithm on Omega Networks for detecting Link Conflicts and switch conflicts. This algorithm can be used to minimize the cross talk problem.

Proceedings ArticleDOI
20 Jul 2015
TL;DR: This approach uses CUDA as parallel programming tool on a GPU in order to take advantage of all available cores and show that the execution time of the fault-tolerance exploration can be significantly reduced.
Abstract: Analyzing the fault-tolerance of interconnection networks implies checking the connectivity of each source-destination pair. The size of the exploration space of such operation skyrockets with the network size and with the number of link faults. However, this problem is highly parallelizable since the exploration of each path between a source-destination pair is independent of the other paths. This paper presents an approach to analyze the fault-tolerance degree of multistage interconnection networks using GPUs in order to speed-up it. This approach uses CUDA as parallel programming tool on a GPU in order to take advantage of all available cores. Results show that the execution time of the fault-tolerance exploration can be significantly reduced.