Search results for "Message passing"

showing 10 items of 17 documents

MARL-Ped+Hitmap: Towards Improving Agent-Based Simulations with Distributed Arrays

2016

Multi-agent systems allow the modelling of complex, heterogeneous, and distributed systems in a realistic way. MARL-Ped is a multi-agent system tool, based on the MPI standard, for the simulation of different scenarios of pedestrians who autonomously learn the best behavior by Reinforcement Learning. MARL-Ped uses one MPI process for each agent by design, with a fixed fine-grain granularity. This requirement limits the performance of the simulations for a restricted number of processors that is lesser than the number of agents. On the other hand, Hitmap is a library to ease the programming of parallel applications based on distributed arrays. It includes abstractions for the automatic parti…

020203 distributed computingComputer scienceDistributed computingMessage passing0202 electrical engineering electronic engineering information engineeringProcess (computing)Reinforcement learning020207 software engineering02 engineering and technologyCrowd simulationGranularityPartition (database)
researchProduct

Big Data in metagenomics: Apache Spark vs MPI.

2020

The progress of next-generation sequencing has lead to the availability of massive data sets used by a wide range of applications in biology and medicine. This has sparked significant interest in using modern Big Data technologies to process this large amount of information in distributed memory clusters of commodity hardware. Several approaches based on solutions such as Apache Hadoop or Apache Spark, have been proposed. These solutions allow developers to focus on the problem while the need to deal with low level details, such as data distribution schemes or communication patterns among processing nodes, can be ignored. However, performance and scalability are also of high importance when…

Big DataComputer and Information SciencesScienceBig dataMessage Passing InterfaceParallel computingResearch and Analysis MethodsComputing MethodologiesComputing MethodologiesComputer ArchitectureComputer SoftwareDatabase and Informatics MethodsSoftwareSpark (mathematics)GeneticsMammalian GenomicsMultidisciplinarybusiness.industryApplied MathematicsSimulation and ModelingQRBiology and Life SciencesComputational BiologySoftware EngineeringGenomicsDNAGenomic DatabasesGenome AnalysisComputer HardwareSupercomputerBiological DatabasesAnimal GenomicsPhysical SciencesScalabilityEngineering and TechnologyMetagenomeMedicineDistributed memoryMetagenomicsbusinessMathematicsAlgorithmsGenome BacterialSoftwareResearch ArticlePLoS ONE
researchProduct

SAUCE: A Web-Based Automated Assessment Tool for Teaching Parallel Programming

2015

Many curricula for undergraduate studies in computer science provide a lecture on the fundamentals of parallel programming like multi-threaded computation on shared memory architectures using POSIX threads or OpenMP. The complex structure of parallel programs can be challenging, especially for inexperienced students. Thus, there is a latent need for software supporting the learning process. Subsequent lectures may cover more advanced parallelization techniques such as the Message Passing Interface (MPI) and the Compute Unified Device Architecture (CUDA) languages. Unfortunately, the majority of students cannot easily access MPI clusters or modern hardware accelerators in order to effectivel…

Class (computer programming)POSIX Threadsbusiness.industryComputer scienceMessage Passing InterfaceParallel computingcomputer.software_genreCUDASoftwareShared memoryVirtual machineWeb applicationbusinesscomputer
researchProduct

Geographical Routing for Delay Tolerant Encounter Networks

2007

Delay Tolerant Networks (DTNs) are intermittently connected networks, where direct end--to--end path between communicating nodes may never exist. To achieve eventual delivery some nodes must store messages and wait opportunity to forward them. In mobile environment, one of the most challenging problems for routing protocols is to decide, which nodes should store the message to achieve eventual delivery as quick as possible. Common approach is to propagate message into large group of nodes, hoping one of them will reach the destination. These solutions, however, are not very scalable as they generate plenty of extra load and traffic to network. Further more, message carriers have no means to…

Delay-tolerant networkingRouting protocolComputer sciencebusiness.industryDistributed computingMessage passingGraph theorycomputer.software_genrelaw.inventionIntelligent agentIntelligent sensorRelaylawScalabilitybusinessWireless sensor networkcomputerComputer network2007 IEEE Symposium on Computers and Communications
researchProduct

Parallelized short read assembly of large genomes using de Bruijn graphs

2011

Abstract Background Next-generation sequencing technologies have given rise to the explosive increase in DNA sequencing throughput, and have promoted the recent development of de novo short read assemblers. However, existing assemblers require high execution times and a large amount of compute resources to assemble large genomes from quantities of short reads. Results We present PASHA, a parallelized short read assembler using de Bruijn graphs, which takes advantage of hybrid computing architectures consisting of both shared-memory multi-core CPUs and distributed-memory compute clusters to gain efficiency and scalability. Evaluation using three small-scale real paired-end datasets shows tha…

Hybrid genome assemblyParallel computingComputational biologyBiologylcsh:Computer applications to medicine. Medical informaticsBiochemistryAssemblersStructural BiologyHumansThroughput (business)Molecular Biologylcsh:QH301-705.5De Bruijn sequenceGenomeContigBacteriaGenome HumanApplied MathematicsMessage passingDNA sequencing theoryComputational BiologyHigh-Throughput Nucleotide SequencingComputer Science Applicationslcsh:Biology (General)comic_booksScalabilitylcsh:R858-859.7comic_books.characterSoftwareResearch ArticleBMC Bioinformatics
researchProduct

VEF Traces: A Framework for Modelling MPI Traffic in Interconnection Network Simulators

2015

Simulation is often used to evaluate the behaviour and measure the performance of computing systems. Specifically, in high-performance interconnection networks, the simulation has been extensively considered to verify the behaviour of the network itself and to evaluate its performance. In this context, network simulation must be fed with network traffic, also referred to as network workload, whose nature has been traditionally synthetic. These workloads can be used for the purpose of driving studies on network performance, but often such workloads are not accurate enough if a realistic evaluation is pursued. For this reason, other non-synthetic workloads have gained popularity over last dec…

InterconnectionNetwork architectureComputer scienceDistributed computingMessage passingMessage Passing InterfaceTraffic modelNetwork performanceContext (language use)Network traffic controlNetwork simulationNetwork traffic simulation2015 IEEE International Conference on Cluster Computing
researchProduct

A Parallel Implementation of the Tree-Structured Self-Organizing Map

2002

This paper presents how Self-Organizing Maps (SOMs)can be trained efficiently using several, simultaneously executing threads on a shared memory Symmetric MultiProcessing (SMP)computer. The training method is a batch version of the Tree-Structured Self-Organizing Map. We note that SMP type of parallel training is very useful for large data sets obtained from nature, the process industry or large document collections, since we do not encounter similar model size limitations as with hardware SOM implementations.

Self-organizing mapTree (data structure)Theoretical computer scienceShared memoryComputer scienceSymmetric multiprocessingMessage Passing InterfaceBatch processingMultiprocessingParallel computingThread (computing)Implementation
researchProduct

A Simulation Framework for Evaluating Distributed Reputation Management Systems

2016

In distributed environments, where interactions involve unknown entities, intelligent techniques for estimating agents’ reputation are required. Reputation Management Systems (RMSs) aim to detect malicious behaviors that may affect the integrity of the virtual community. However, these systems are highly dependent of the application domain they address; hence the evaluation of different RMSs in terms of correctness and resistance to security attacks is frequently a tricky task. In this work we present a simulation framework to support researchers in the assessment of a RMS. The simulator is organized in two logic layers where network nodes are mapped to system processes that implement the i…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniCorrectnessComputer scienceDistributed computingmedia_common.quotation_subjectComputer Science (all)Message Passing InterfaceSimulation framework020206 networking & telecommunications02 engineering and technologyComputer securitycomputer.software_genreTask (project management)Distributed reputation managementControl and Systems EngineeringApplication domain020204 information systemsSynchronization (computer science)0202 electrical engineering electronic engineering information engineeringMultiagent systemcomputerReputation managementVirtual communityReputationmedia_common
researchProduct

A Lightweight Software Architecture for Robot Navigation and Visual Logging through Environmental Landmarks Recognition

2006

A robot architecture with real-time performance in navigation tasks is presented. The system architecture is multi-threaded with shared memory and fast message passing through static signalling. In this paper, we focused on the reactive layer components and its straightforward implementation. The proposed architecture is described with reference to an experimental setup, in which the robot task is visual logging of environmental landmarks detected on the basis of sensor readings. Our experimental results show how the robot is able to identify, make snapshots and log a set of landmarks by matching 2D geometric patterns.

Shared memoryComputer sciencebusiness.industryMessage passingReal-time computingSystems architectureRobotComputer visionArtificial intelligencePattern matchingSoftware architecturebusinessMobile robot navigation2006 International Conference on Parallel Processing Workshops (ICPPW'06)
researchProduct

Design of SCMA Codebooks using Differential Evolution

2020

Non-orthogonal multiple access (NOMA) is a promising technology which meets the demands of massive connectivity in future wireless networks. Sparse code multiple access (SCMA) is a popular code-domain NOMA technique. The effectiveness of SCMA comes from: (1) the multi-dimensional sparse codebooks offering high shaping gain and (2) sophisticated multi-user detection based on message passing algorithm (MPA). The codebooks of the users play the main role in determining the performance of SCMA system. This paper presents a framework to design the codebooks by taking into account the entire system including the SCMA encoder and the MPA-based detector. The symbol-error rate (SER) is considered as…

Signal Processing (eess.SP)FOS: Computer and information sciencesComputer scienceWireless networkInformation Theory (cs.IT)Computer Science - Information Theory05 social sciencesMessage passingDetector050801 communication & media studiesmedicine.diseaseNoma0508 media and communicationsComputer engineeringDifferential evolution0502 economics and businessFOS: Electrical engineering electronic engineering information engineeringmedicineCode (cryptography)050211 marketingMinificationElectrical Engineering and Systems Science - Signal ProcessingEncoder2020 IEEE International Conference on Communications Workshops (ICC Workshops)
researchProduct