563 research outputs found
Not so social media: Twitter use in the conference sector
No full textThis research forms part of a larger project funded by Meeting Professionals International (MPI) focusing on the future of business events . In this paper we investigate the motivations for social media use within a professional event context. Twitter was tracked before during and after seven conferences and from this the top tweeters and organisers were identified. Fifteen interviews were conducted into both the organisational strategy and individual motivations for tweeting and were analysed alongside interviews with five social media experts. The research highlights several potential areas of conflict. Social media use tends to focus on broadcasting information rather than encouraging dialogue. People only tweet if they gain personal or individual professional value from doing so and event organisers need a deeper understanding of what that value is. Monitoring social media to gain customer insights and develop a more responsive customer service strategy is not yet happening although it is recognised as a necessity. The silent majority (passives) need to be better understood and catered for through social media use. Overall this sector, which successfully creates social interactions offline appears to be failing to do so online. A more strategic and resourced approach to social media is needed if its potential is to be achieved
Portable Application-level Checkpointing for Hybrid MPI-OpenMP Applications
No full textAbstractAs parallel machines increase their number of processors, so does the failure rate of the global system, thus, long-running applications will need to make use of fault tolerance techniques to ensure the successful execution completion. Most of current HPC systems are built as clusters of multicores. The hybrid MPI-OpenMP paradigm provides numerous benefits on these systems. This paper presents a checkpointing solution for hybrid MPI-OpenMP applications, in which checkpoint consistency is guaranteed by using a coordination protocol intra-node, while no inter-node coordination is needed. The proposal reduces network utilization and storage resources in order to optimize the I/O cost of fault tolerance, while minimizing the checkpointing overhead. Besides, the portability of the solution and the dynamic parallelism provided by OpenMP enable the restart of the applications using machines with different architectures, operating systems and/or number of cores, adapting the number of running OpenMP threads for the best exploitation of the available resources. Extensive evaluation using hybrid MPI-OpenMP applications from the ASC Sequoia Benchmark Codes and NERSC-8/Trinity benchmarks is presented, showing the effectiveness and efficiency of the approach
Parallel Programming with MPI through Gaming
No full textMangel på erfaring med parallell programmering blant programmerere er en økende bekymring. Dette er problematisk ettersom parallell programmering kreves for å utnytte komponenter som GPUer og flerkjerne-CPUer fullt ut. Vi tar opp dette problemet i oppgaven vår ved å bygge et miljø for å lære parallell programmering med MPI. MPI er en av de dominerende programmeringsutvidelsene for programmering av svært parallelle systemer. Gjennom å utvikle et edutainment-spill som simulerer MPI-miljøet, har vi til hensikt å gjøre prosessen med å gjøre programmerere kjent med MPI morsommere og mer interessant.
Avhandlingsarbeidet vårt er en forlengelse av arbeidet som er gjort som en del av forfatterens høstprosjekt.
For å forbedre MPI-spillet vårt vurderer vi standard kvalitative spillegenskaper som kan påvirke spillernes engasjement i spillet. Disse vurderingene inkluderer passende spillvanskeligheter, begrensende nye spillopplevelser og en kortfattet spillveiledning. Ved utvikling av spillet tar vi også hensyn til vårt valg og illustrasjon av MPI-funksjoner samtidig som vi legger til flere MPI-funksjoner.
Vi bruker også resultatene fra en tidligere brukerstudie, samt en brukerstudie til vårt utvidede arbeid. Sistnevnte prøver å bestemme spillets fornøyelse og spillevanskelighet, samt spillernes opplevde læring og interesse for feltet parallellprogrammering.
Noen av de tekniske og konseptuelle utfordringene vi møtte ved å lage et edutainmentspill nettopp for å gjøre en bruker kjent med parallell programmering blir også beskrevet.
Spesifikt, diskuterer vi vårt valg av å bruke Unity-spillmotoren og hvordan vi brukte en tilnærming der spillere visuelt kan programmere inne i spillet med MPI. MPI-prosessene simuleres av roboter. Videre er spillelementer implementert for å abstrahere ut kode som, for eksempel, inversjon av en pikselfarge.
Brukere kan også legge til og se på de underliggende MPI-kodene som styrer disse robotene.
Simulerte MPI-funksjoner inkluderer MPI_Init, MPI_Finalize, MPI_Comm_rank, MPI_Send, MPI_Recv, MPI_Bcast, MPI_Scatter, MPI_Gather og MPI_Sendrecv.
Vår siste brukerstudie viste at dette spillet har mye potensial. En diskusjon av flere veier for fremtidig arbeid er også inkludert.Lack of experience with parallel programming among programmers is a growing concern. This is problematic as parallel programming is required to fully utilize components such as GPUs and multi-core CPUs. We address this problem in our thesis by building an environment for learning parallel programming with MPI. MPI is one of the dominating programming extensions for programming highly parallel systems. Through developing an edutainment game that simulates the MPI environment, we intend to make the process of familiarizing programmers with MPI more fun and interesting.
Our thesis work is an extension of the work done as part of the author´s fall project.
In enhancing our MPI game, we consider standard qualitative gaming characteristics that might impact players' engagement in the game. These considerations include appropriate game difficulty, limiting new game experiences, and a concise game tutorial. While further developing the game, we are cognizant of our choice and illustration of MPI-functions while, at the same time, implementing several new MPI-functions.
We also make use of the results from a prior user study, as well as a user study conducted for our extended work. The latter tries to determine the game's enjoyability and game difficulty, as well as players' perceived learning and interest in the field of parallel programming.
Some of the technical and conceptual challenges we faced when making an edutainment game, precisely for familiarizing a user with parallel programming, are also described.
In particular, we discuss our choice of using the Unity game engine and how we used an approach where players can visually program inside the game with MPI. The MPI processes are simulated by robots. Furthermore, game-elements are implemented to abstract out code such as inversion of a pixel color.
Users are also able to add to and look at the underlying MPI codes that control these robots.
MPI functions simulated include MPI_Init, MPI_Finalize, MPI_Comm_rank, MPI_Send, MPI_Recv, MPI_Bcast, MPI_Scatter, MPI_Gather and MPI_Sendrecv.
Our final user study showed this game has a lot of potential. A discussion of several avenues for future work is also included
MSAProbs-MPI: parallel multiple sequence aligner for distributed-memory systems
No full textThis is a pre-copyedited, author-produced version of an article accepted for publication in Bioinformatics following peer review. The version of recordJorge González-Domínguez, Yongchao Liu, Juan Touriño, Bertil Schmidt; MSAProbs-MPI: parallel multiple sequence aligner for distributed-memory systems, Bioinformatics, Volume 32, Issue 24, 15 December 2016, Pages 3826–3828, https://doi.org/10.1093/bioinformatics/btw558is available online at: https://doi.org/10.1093/bioinformatics/btw558[Abstracts] MSAProbs is a state-of-the-art protein multiple sequence alignment tool based on hidden Markov models. It can achieve high alignment accuracy at the expense of relatively long runtimes for large-scale input datasets. In this work we present MSAProbs-MPI, a distributed-memory parallel version of the multithreaded MSAProbs tool that is able to reduce runtimes by exploiting the compute capabilities of common multicore CPU clusters. Our performance evaluation on a cluster with 32 nodes (each containing two Intel Haswell processors) shows reductions in execution time of over one order of magnitude for typical input datasets. Furthermore, MSAProbs-MPI using eight nodes is faster than the GPU-accelerated QuickProbs running on a Tesla K20. Another strong point is that MSAProbs-MPI can deal with large datasets for which MSAProbs and QuickProbs might fail due to time and memory constraints, respectively
Implementation and validation of a model of the MPI Stewart platform
No full textA simulated model of the MPI Stewart platform can be used to identify the influence of motion system characteristics on human control behaviour in active closed-loop control experiments on the SIMONA Research Simulator. In this paper, a previously identified model of the MPI Stewart platform was analysed with describing function measurements, and it was found that a reduced form of the model was sufficient to capture the relevant dynamics. The reduced model was simulated on the SIMONA Research Simulator and describing function measurements were performed with two IMUs. Both IMUs revealed a resonance peak in measurements of response magnitude at the highest frequencies. A reduced time delay was found with the newer IMU. With the describing function measurements, the implementation of the MPI Stewart platform model was validated in terms of the frequency response and the time delay.Control & OperationsAerospace Engineerin
In-vitro MPI-guided IVOCT catheter tracking in real time for motion artifact compensation
No full textThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Purpose Using 4D magnetic particle imaging (MPI), intravascular optical coherence tomography (IVOCT) catheters are tracked in real time in order to compensate for image artifacts related to relative motion. Our approach demonstrates the feasibility for bimodal IVOCT and MPI in-vitro experiments. Material and methods During IVOCT imaging of a stenosis phantom the catheter is tracked using MPI. A 4D trajectory of the catheter tip is determined from the MPI data using center of mass sub-voxel strategies. A custom built IVOCT imaging adapter is used to perform different catheter motion profiles: no motion artifacts, motion artifacts due to catheter bending, and heart beat motion artifacts. Two IVOCT volume reconstruction methods are compared qualitatively and quantitatively using the DICE metric and the known stenosis length. Results The MPI-tracked trajectory of the IVOCT catheter is validated in multiple repeated measurements calculating the absolute mean error and standard deviation. Both volume reconstruction methods are compared and analyzed whether they are capable of compensating the motion artifacts. The novel approach of MPI-guided catheter tracking corrects motion artifacts leading to a DICE coefficient with a minimum of 86% in comparison to 58% for a standard reconstruction approach. Conclusions IVOCT catheter tracking with MPI in real time is an auspicious method for radiation free MPI-guided IVOCT interventions. The combination of MPI and IVOCT can help to reduce motion artifacts due to catheter bending and heart beat for optimized IVOCT volume reconstructions
Design of Multivariable PI Controller Using Evolutionary Algorithms for VSP based AC/DC Interconnected Systems
No full textA new application of Multivariable Proportional-Integral (MPI) controller with using evolutionary algorithms for a VSP based AC/DC interconnected power system model is proposed. The VSP based HVDC model is added for mitigation of system frequency dynamics by emulating virtual inertia. The designed heuristic-based multivariable PI controller is proposed for better performance of the system's states during contingencies. The proposed MPI (MPI) controller is modified by adding optimisation-based evolutionary algorithms to improve characteristic performance model versus conventional control methods. Simulations results demonstrate how the proposed MPI controller can optimally improve the performance of the power system, especially when a VSP base inertia emulation is activated in the system.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Intelligent Electrical Power Grid
Runtime support for irregular computation in MPI-based applications
No full textIn recent years there are increasing number of applications that have been using irregular computation models in various domains, such as computational chemistry, bioinformatics, nuclear reactor simulation and social network analysis. Due to the irregular and data-dependent communication patterns and sparse data structures involved in those applications, the traditional parallel programming model and runtime need to be carefully designed and implemented in order to accommodate the performance and scalability requirements of those irregular applications on large-scale systems.
The Message Passing Interface (MPI) is the industry standard communication library for high performance computing. However, whether MPI can serve as a suitable programming model / runtime for irregular applications or not is one of the most debated aspects in the community. The goal of this thesis is to investigate the suitability of MPI to irregular applications.
This thesis consists of two subtopics. The first subtopic focuses on improving MPI runtime to support the irregular applications from perspective of scalability and performance. The first three parts in this subtopic focus on MPI one-sided communication. In the first part, we present a thorough survey of current MPI one-sided implementations and illustrate scalability limitations in those implementations. In the second part, we propose a new design and implementation of MPI one-sided communication, called ScalaRMA, to effectively address those scalability limitations. The third part in this subtopic focuses on various issuing strategies in MPI one-sided communication. We propose an adaptive issuing strategy which can adaptively choose between delayed issuing strategy and eager issuing strategy in MPI runtime to achieve high performance based on current communication volume in MPI-based application. The last part in this subtopic is to tackle the scalability limitations in the virtual connection (VC) objects in MPI implementation. We propose a scalable design to reduce the memory consumption of VC objects in MPI runtime.
The second subtopic of this thesis focuses on improving MPI programming model to better support the irregular applications. Traditional two-sided data movement model in MPI standard designed for scientific computation provides a paradigm for user to specify how to move the data between processes, however, it does not provide interface to flexibly manage the computation, which means user needs to explicitly manage where the computation should be performed. This model is not well suited for irregular applications which involve irregular and data-dependent communication pattern. In this work, we combine Active Messages (AM), an alternative programming paradigm which is more suitable for irregular computations, with traditional MPI data movement model, and propose a generalized MPI-interoperable Active Messages framework (MPI-AM). The framework allows MPI-based applications to incrementally use AMs only when necessary, avoiding rewriting the entire MPI-based application. Such framework integrates data movement and computation together in the programming model and MPI can coordinate the computation and communication in a much more flexible manner. In this subtopic, we propose several strategies including message streaming, buffer management and asynchronous processing, in order to efficiently handle AMs inside MPI. We also propose subtle correctness semantics of MPI-AM to define how AMs can work correctly with other MPI messages in the system, from perspectives of memory consistency, concurrency, ordering and atomicity.Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2018-05-01The student, Xin Zhao, accepted the attached license on 2016-04-19 at 17:35.The student, Xin Zhao, submitted this Dissertation for approval on 2016-04-19 at 17:41.This Dissertation was approved for publication on 2016-04-20 at 16:46.DSpace SAF Submission Ingestion Package generated from Vireo submission #9354 on 2016-07-07 at 14:17:29Made available in DSpace on 2016-07-07T21:17:49Z (GMT). No. of bitstreams: 3
ZHAO-DISSERTATION-2016.pdf: 4394484 bytes, checksum: 5ba06e852848b9ba1faecfac0bd40728 (MD5)
LICENSE.txt: 4205 bytes, checksum: 53574e861600415f1b76f750d3c6cee6 (MD5)
PROQUEST_LICENSE.txt: 4551 bytes, checksum: 473c39fac8db59853f60cf6f9b8724fb (MD5)
Previous issue date: 2016-04-20Embargo set by: Seth Robbins for item 93288
Lift date: 2018-07-07T21:18:16Z
Reason: Author requested closed access (OA after 2yrs) in Vireo ETD systemLimited Restriction Lifted for Item 93288 on 2018-07-08T09:15:20Z
MPI/Open-MP Hybridization of Higher Order WENO Scheme for the Incompressible Navier-Stokes Equations
No full textCopyright by authors. Posted on SOAR with author permission.With the contemporary emerging transition for the past two decades in high
performance computing (HPC) towards clusters of nodes, it is possible to obtain an
efficiently scalable CFD code by hybridization of Message Passing Interface (MPI) and Open
Multi-Processing (Open-MP). The parallelization of an incompressible higher order DNS
solver using Navier-Stokes equations utilizing WENO (weighted Essentially Non-Oscillatory)
scheme is presented in this paper. Initially, a time dependent two dimensional diffusion
equation was parallelized by MPI in an effort to explore the concepts. Subsequently, the
procedure is extended with several advanced MPI routines for the parallelization of higher
order finite-difference schemes. The parallelized code is subsequently examined on a
benchmark problem for incompressible flows – lid driven cavity. The results of the
developed code were compared and validated with the serial model. The overall objective is
to achieve the best performance of the incompressible Navier-Stokes solver by carefully
implementing, profiling and optimizing both MPI communications and Open-MP
parallelization. The results demonstrate that, incorporating Open-MP parallelization
technique contributes a slight advantage in performance relative to pure MPI
implementation. MPI processes are limited by the number of communicators and grid size of
the simulation. However, fine grain parallelization is possible by incorporating Open-MP
threads in certain segments of the code
- …
