Showing papers in "Journal of Parallel and Distributed Computing in 2015"
••
TL;DR: This paper discusses approaches and environments for carrying out analytics on Clouds for Big Data applications, and identifies possible gaps in technology and provides recommendations for the research community on future directions on Cloud-supported Big Data computing and analytics solutions.
773 citations
••
[...]
TL;DR: A new taxonomy for reputation systems is introduced, along with: a reference model for reputation context, a model of reputation systems, a substantial survey, and a comparison of existing reputation research and deployed reputation systems.
180 citations
••
TL;DR: This paper introduces immoveable dataset concept which constrains the movement of certain datasets due to security and cost considerations and proposes a new scheduling model in the context of Cloud systems, which holds an economical distribution of tasks among the available CSPs (Cloud Service Providers) in the market.
98 citations
••
TL;DR: This work proposes a framework for SpGEMM on GPUs and emerging CPU-GPU heterogeneous processors using the CSR format, and proposes an efficient parallel insert method for long rows of the resulting matrix and develops a heuristic-based load balancing strategy.
90 citations
••
TL;DR: An energy efficiency evaluation of Hadoop on physical and virtual clusters in different configurations and a discussion on the implications of using cloud environments for big data analyses are presented.
66 citations
••
TL;DR: A heterogeneity-driven task scheduling algorithm called Heterogeneous Selection Value (HSV) based on the classic model, and a end-to-end synchronized Scheduling Value on Communication Contentionbased on the communication contention model are proposed to address the above problems.
63 citations
••
TL;DR: Compared to the state-of-the-art methods which only minimize the total communication volume, it is shown on a large number of problem instances that UMPa produces better partitions in terms of several communication metrics.
59 citations
••
[...]
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
••
TL;DR: Both theoretical analysis and simulation results show that the proposed RBR scheme can protect location privacy of sinks effectively and can have high network lifetime, high network security and high energy efficiency.
50 citations
••
TL;DR: Three novel approaches for the task scheduling problem using recently proposed Directed Search Optimization (DSO) are introduced using DSO as a training algorithm to train a three layer Artificial Neural Network and then Radial Basis Function Neural Networks (RBFNN).
50 citations
••
TL;DR: The multilevel paradigm is applied to the modularity graph clustering problem, improving upon the state of the art by introducing new efficient methods for coarsening graphs, creating initial clusterings, and performing local refinement on the resulting clusterings.
••
TL;DR: This work proposes parallel algorithms to compute centrality on accelerators by allowing a GPU to execute multiple BFSs at the same time and exploits hardware and software vectorization to compute closeness centrality values on CPUs, GPUs and Intel Xeon Phi.
••
TL;DR: An adaptive algorithm for monitoring big data applications that adapts the intervals of sampling and frequency of updates to data characteristics and administrator needs is presented that reduces monitoring costs significantly without penalizing data quality.
••
TL;DR: This study evaluates the computing and energy performance of two well-known irregular NP-hard problems-the Traveling-Salesman Problem and K-Means clustering-and a numerical seismic wave propagation simulation kernel-Ondes3D-on multicore, NUMA, and manycore platforms.
••
TL;DR: A new parallel algorithm for MCE, Parallel Enumeration of Cliques using Ordering ( PECO), designed for the MapReduce framework, which can effectively process a variety of large real-world graphs with millions of vertices and tens of millions of maximal cliques, and scales well with the degree of available parallelism.
••
TL;DR: The new Householder reconstruction algorithm allows us to design more efficient parallel QR algorithms, with significantly lower latency cost compared to Householder QR and lower bandwidth and latency costs compared with Communication-Avoiding QR (CAQR) algorithm.
••
TL;DR: In this paper, the authors designed and implemented MIC-SVM, a highly efficient parallel SVM for x86 based multi-core and many-core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi co-processor (MIC).
••
TL;DR: This paper introduces CR-OLAP, a scalable Cloud based Real-time OLAP system based on a new distributed index structure for OLAP, the distributed PDCR tree, and studies the use of parallel computing on scalable clouds to accelerate queries.
••
TL;DR: By reduction to an oracle-model, it is proved that the population protocol model extended with a cover-time service is at least as strong as a Turing Machine of space log n with input commutativity, where n is the number of nodes in the network.
••
TL;DR: This work proposes task scheduling algorithms that leverage per-core DVFS on multi-cores and achieves a balance between performance and energy consumption and analyzes and derives algorithms with low time complexity for each mode.
••
TL;DR: The potential for speeding up CA execution using multi-core CPUs and GPUs is investigated and the scalability of doing so with respect to standard CA parameters such as lattice and neighbourhood sizes, number of states and generations is determined.
••
TL;DR: In this article, an adaptive reinforcement learning (RL) approach is proposed to improve successful execution with low computational complexity using an emerging methodology of RL in conjunction with neural network to help a scheduler that effectively observes and adapts to dynamic changes in execution environments.
••
TL;DR: This paper addresses the problem of convergecast in a wireless sensor network that uses time division multiplexing in order to schedule its node-to-node communication in a time-bounded manner and proposes a heuristic solution based on time slot assignments.
••
TL;DR: A theoretical framework called the Knapsack-based Message Scheduling and Drop strategy in Theory (KMSDT) based on Epidemic routing protocol is presented and a practical framework called KMSDP and KMSDT achieve better delivery ratio than other congestion control strategies.
••
TL;DR: In this paper, an interface and an implementation of the General Matrix Multiply (GEMM) routine for multiple small matrices processed simultaneously on NVIDIA graphics processing units (GPUs).
••
TL;DR: It is shown that the parallel Tabu Search algorithm for graphics cards (GPUs) outperforms other existing Tabu search approaches in terms of quality of solutions and the number of evaluated schedules per second.
••
[...]
TL;DR: This paper describes and evaluates a fault tolerant distributed aggregation technique, Flow Updating, which overcomes the problems in previous averaging approaches and is able to operate on faulty dynamic networks.
••
TL;DR: A new approach for solving the All-Pairs Shortest-Path (APSP) problem for planar graphs that exploits the massive on-chip parallelism available in today's Graphics Processing Units (GPUs) is presented and two new algorithms are described based on this approach.
••
TL;DR: This paper introduces a methodology for assessing the ability of a suite of "miniapps" to effectively represent a key performance characteristic in a full application code, and demonstrates this methodology using four applications and their proxies.
••
TL;DR: This work studies tradeoffs between the amount of information (advice) available a priori to the agents and the cost (number of edge traversals) of rendezvous and treasure hunt to find the smallest size of advice which enables the agents to solve these tasks at some cost C in a network with e edges.