I propose an applications-first approach for adjusting how parallel and distributed computing concepts are incorporated into curricula. By focusing on practical applications that leverage parallelism and distributed systems, this approach aims to make these complex topics more accessible and engaging for both CS and non-CS majors. An applications-first approach demonstrates the advantages of parallel and distributed computing in solving real-world problems while building practical experience and skills before delving into theoretical concepts. This could potentially broaden the appeal and retention of these concepts. I highlight some example application-centric efforts, and conclude with questions that could be investigated in the service of exploring applications-first approaches.
This is a short survey of ten algorithms that are often used for military purposes, followed by analysis of their potential suitability for dataflow and GaAs, which are a specific architecture and technology for supercomputers on a chip, respectively. Whenever an algorithm or a device is used in military settings, it is natural to assume strict requirements related to speed, reliability, scale, energy, size, and accuracy. The two aforementioned paradigms seem to be promising in fulfilling most of these requirements.
Mengchen Wang, Nicolas Ferey, Patrick Bourdot
et al.
This paper discusses about the advantage of using asynchronous simulation in the case of interactive simulation in which user can steer and control parameters during a simulation in progress. synchronous models allow to compute each iteration faster to address the issues of performance needed in an highly interactive context, and our hypothesis is that get partial results faster is better than getting synchronized and final results to take a decision, in a interactive simulation context.
Due to importance of reducing of time solution in numerical codes, we propose an algorithm for parallel LU decomposition solver for dense and sparse matrices on GPU. This algorithm is based on first bi-vectorizing a triangular matrices of decomposed coefficient matrix and then equalizing vectors. So we improve performance of LU decomposition on equal contributed scheme on threads. This algorithm also is convenient for other parallelism method and multi devices. Several test cases show advantage of this method over other familiar method.
Laplace transform method has proved to be very efficient and easy to parallelize for the solution of time-dependent problems. However, the synchronization delay among processors implies an upper bound on the expectable acceleration factor, which leads to a lot of wasted time. In this paper, we propose an original asynchronous Laplace transform method formalized for quasilinear problems based on the well-known Gaver-Stehfest algorithm. Parallel experiments show the convergence of our new method, as well as several interesting properties compared with the classical algorithms.
Geoffrey C. Fox, Vatche Ishakian, Vinod Muthusamy
et al.
This whitepaper summarizes issues raised during the First International Workshop on Serverless Computing (WoSC) 2017 held June 5th 2017 and especially in the panel and associated discussion that concluded the workshop. We also include comments from the keynote and submitted papers. A glossary at the end (section 8) defines many technical terms used in this report.
An algorithm for $n-1$-strong-equillibrium for distributed consensus in a ring with rational agents was proposed by Afek et al. (2014). A proof of impossibility of $n-1$-strong-equillibrium for distributed consensus in every topology with rational agents, when $n$ is even, is presented. Furthermore, we show that the algorithm proposed by Afek et al. is the only algorithm which can solve the problem when $n$ is odd. Finally, we prove that the proposed algorithm provides a $n-2$-strong-equillibrium in a synchronous ring when $n$ is even.
We give a simple deterministic constant-round algorithm in the congested clique model for reducing the number of edges in a graph to $n^{1+\varepsilon}$ while preserving the minimum spanning forest, where $\varepsilon > 0$ is any constant. This implies that in the congested clique model, it is sufficient to improve MST and other connectivity algorithms on graphs with slightly superlinear number of edges to obtain a general improvement. As a byproduct, we also obtain a simple alternative proof showing that MST can be computed deterministically in $O(\log \log n)$ rounds.
Even though virtualization provides a lot of advantages in cloud computing, it does not provide effective performance isolation between the virtualization machines. In other words, the performance may get affected due the interferences caused by co-virtual machines. This can be achieved by the proper management of resource allocations between the Virtual Machines running simultaneously. This paper aims at providing a proposed novel architecture that is based on Fast Genetic K-means++ algorithm and test results show positive improvements in terms of performance improvements over a similar existing approach.
In the context of large-scale networks, the consideration of faults is an evident necessity. This document is focussing on the self-stabilizing approach which aims at conceiving algorithms "repairing themselves" in case of transient faults, that is of faults implying an arbitrary modification of the states of the processes. The document focuses on two different contexts, covering the major part of my research work these last years. The first part of the document is dedicated to the design and analysis of self-stabilizing algorithms for networks of processes. The second part of the document is dedicated to the design and analysis of self-stabilizing algorithms for autonomous entities (i.e., software agents, robots, etc.) moving in a network.
Process migration refers to the act of transferring a process in the middle of its execution from one machine to another in a network. In this paper, we proposed a process migration framework for Linux OS. It is a multilayer architecture to confine every functionality independent section of the system in separate layer. This architecture is capable of supporting diverse applications due to generic user space interface and dynamic structure that can be modified according to demands.
While for single processor and SMP machines, memory is the allocatable quantity, for machines made up of large amounts of parallel computing units, each with its own local memory, the allocatable quantity is a single computing unit. Where virtual address management is used to keep memory coherent and allow allocation of more than physical memory is actually available, virtual communication channel references can be used to make computing units stay connected across allocation and swapping.
Modern distributed systems use names everywhere. Lockservices such as Chubby and ZooKeeper provide an effective mechanism for mapping from application names to server instances, but proper usage of them requires a large amount of error-prone boiler-plate code. Application programmers often try to write wrappers to abstract away this logic, but it turns out there is a more general and easier way of handling the issue. We show that by extending the existing name resolution capabilities of RPC libraries, we can remove the need for such annoying boiler-plate code while at the same time making our services more robust.
The emergence of cloud computing has enabled an incredible growth in available hardware resources at very low costs. These resources are being increasingly utilized by corporations for scalable analysis of "big data" problems. In this work, we explore the possibility of using commodity hardware such as Amazon EC2 for performing large scale scientific computation. In particular, we simulate interconnected cortical neurons using MapReduce. We build and model a network of 1000 spiking cortical neurons in Hadoop, an opensource implementation of MapReduce, and present results.
Service-oriented infrastructures pose new challenges in a number of areas, notably with regard to security and dependability. BT has developed a combination of innovative security solutions and governance frameworks that can address these challenges. They include advances in identity federation; distributed usage and access management; context-aware secure messaging, routing and transformation; and (security) policy governance for service-oriented architectures. This paper discusses these developments and the steps being taken to validate their functionality and performance.
Ioannis Liabotis, Ognjen Prnjat, Tope Olukemi
et al.
This paper presents basic concepts, architectural principles and algorithms for efficient resource and security management in cluster computing environments and the Grid. The work presented in this paper is funded by BTExacT and the EPSRC project SO-GRM (GR/S21939).
Sorting is one of the classic problems of computer science. Whilst well understood on sequential machines, the diversity of architectures amongst parallel systems means that algorithms do not perform uniformly on all platforms. This document describes the implementation of a radix based algorithm for sorting positive integers on a Fujitsu AP1000 Supercomputer, which was constructed as an entry in the Joint Symposium on Parallel Processing (JSPP) 1994 Parallel Software Contest (PSC94). Brief consideration is also given to a full radix sort conducted in parallel across the machine.
We discuss the use of both MPI and OpenMP in the teaching of senior undergraduate and junior graduate classes in parallel programming. We briefly introduce the OpenMP standard and discuss why we have chosen to use it in parallel programming classes. Advantages of using OpenMP over message passing methods are discussed. We also include a brief enumeration of some of the drawbacks of using OpenMP and how these drawbacks are being addressed by supplementing OpenMP with additional MPI codes and projects. Several projects given in my class are also described in this paper.