Data-parallel computation in parallel and distributed environments

The past few decades have seen a considerable increase in the number of parallel and distributed systems. With the development of more complex applications, the need for more powerful systems has emerged and various parallel and distributed environments have been designed and implemented. Each of the environments, including hardware and software, has unique strengths and weaknesses. There is no single parallel environment that can be identified as the best environment for all applications with respect to hardware and software properties. The main goal of this thesis is to provide a novel way of performing data-parallel computation in parallel and distributed environments by utilizing the best characteristics of difference aspects of parallel computing. For the purpose of this thesis, three aspects of parallel computing were identified and studied. First, three parallel environments (shared memory, distributed memory, and a network of workstations) are evaluated to quantify theirsuitability for different parallel applications. Due to the parallel and distributed nature of the environments, networks connecting the processors in these environments were investigated with respect to their performance characteristics. Second, scheduling algorithms are studied in order to make them more efficient and effective. A concept of application-specific information scheduling is introduced. The application- specific information is data about the workload extractedfrom an application, which is provided to a scheduling algorithm. Three scheduling algorithms are enhanced to utilize the application-specific information to further refine their scheduling properties. A more accurate description of the workload is especially important in cases where the workunits are heterogeneous and the parallel environment is heterogeneous and/or non-dedicated. The results obtained show that the additional information regarding the workload has a positive impact on the performance of applications. Third, a programming paradigm for networks of symmetric multiprocessor (SMP) workstations is introduced. The MPIT programming paradigm incorporates the Message Passing Interface (MPI) with threads to provide a methodology to write parallel applications that efficiently utilize the available resources and minimize the overhead. The MPIT allows for communication and computation to overlap by deploying a dedicated thread for communication. Furthermore, the programming paradigm implements an application-specific scheduling algorithm. The scheduling algorithm is executed by the communication thread. Thus, the scheduling does not affect the execution of the parallel application. Performance results achieved from the MPIT show that considerable improvements over conventional MPI applications are achieved.

Video transcoding in a distributed cloud computing environment

Video transcoding refers to the process of converting a digital video from one format into another format. It is a compute-intensive operation. Therefore, transcoding of a large number of simultaneous video streams requires a large amount of computing resources. Moreover, to handle di erent load conditions in a cost-e cient manner, the video transcoding service should be dynamically scalable. Infrastructure as a Service Clouds currently offer computing resources, such as virtual machines, under the pay-per-use business model. Thus the IaaS Clouds can be leveraged to provide a coste cient, dynamically scalable video transcoding service. To use computing resources e ciently in a cloud computing environment, cost-e cient virtual machine provisioning is required to avoid overutilization and under-utilization of virtual machines. This thesis presents proactive virtual machine resource allocation and de-allocation algorithms for video transcoding in cloud computing. Since users' requests for videos may change at di erent times, a check is required to see if the current computing resources are adequate for the video requests. Therefore, the work on admission control is also provided. In addition to admission control, temporal resolution reduction is used to avoid jitters in a video. Furthermore, in a cloud computing environment such as Amazon EC2, the computing resources are more expensive as compared with the storage resources. Therefore, to avoid repetition of transcoding operations, a transcoded video needs to be stored for a certain time. To store all videos for the same amount of time is also not cost-e cient because popular transcoded videos have high access rate while unpopular transcoded videos are rarely accessed. This thesis provides a cost-e cient computation and storage trade-o strategy, which stores videos in the video repository as long as it is cost-e cient to store them. This thesis also proposes video segmentation strategies for bit rate reduction and spatial resolution reduction video transcoding. The evaluation of proposed strategies is performed using a message passing interface based video transcoder, which uses a coarse-grain parallel processing approach where video is segmented at group of pictures level.

Implantation des futures sur un système distribué par passage de messages

Ce mémoire présente une implantation de la création paresseuse de tâches desti- née à des systèmes multiprocesseurs à mémoire distribuée. Elle offre un sous-ensemble des fonctionnalités du Message-Passing Interface et permet de paralléliser certains problèmes qui se partitionnent difficilement de manière statique grâce à un système de partitionnement dynamique et de balancement de charge. Pour ce faire, il se base sur le langage Multilisp, un dialecte de Scheme orienté vers le traitement parallèle, et implante sur ce dernier une interface semblable à MPI permettant le calcul distribué multipro- cessus. Ce système offre un langage beaucoup plus riche et expressif que le C et réduit considérablement le travail nécessaire au programmeur pour pouvoir développer des programmes équivalents à ceux en MPI. Enfin, le partitionnement dynamique permet de concevoir des programmes qui seraient très complexes à réaliser sur MPI. Des tests ont été effectués sur un système local à 16 processeurs et une grappe à 16 processeurs et il offre de bonnes accélérations en comparaison à des programmes séquentiels équiva- lents ainsi que des performances acceptables par rapport à MPI. Ce mémoire démontre que l’usage des futures comme technique de partitionnement dynamique est faisable sur des multiprocesseurs à mémoire distribuée.

A novel parallel approach to the likelihood-based estimation of admixture in population genetics

Inferring population admixture from genetic data and quantifying it is a difficult but crucial task in evolutionary and conservation biology. Unfortunately state-of-the-art probabilistic approaches are computationally demanding. Effectively exploiting the computational power of modern multiprocessor systems can thus have a positive impact to Monte Carlo-based simulation of admixture modeling. A novel parallel approach is briefly described and promising results on its message passing interface (MPI)-based C implementation are reported.

Parallel performance and scalability experiments with the Danish Eulerian Model on the EPCC supercomputers

The Danish Eulerian Model (DEM) is a powerful air pollution model, designed to calculate the concentrations of various dangerous species over a large geographical region (e.g. Europe). It takes into account the main physical and chemical processes between these species, the actual meteorological conditions, emissions, etc.. This is a huge computational task and requires significant resources of storage and CPU time. Parallel computing is essential for the efficient practical use of the model. Some efficient parallel versions of the model were created over the past several years. A suitable parallel version of DEM by using the Message Passing Interface library (AIPI) was implemented on two powerful supercomputers of the EPCC - Edinburgh, available via the HPC-Europa programme for transnational access to research infrastructures in EC: a Sun Fire E15K and an IBM HPCx cluster. Although the implementation is in principal, the same for both supercomputers, few modifications had to be done for successful porting of the code on the IBM HPCx cluster. Performance analysis and parallel optimization was done next. Results from bench marking experiments will be presented in this paper. Another set of experiments was carried out in order to investigate the sensitivity of the model to variation of some chemical rate constants in the chemical submodel. Certain modifications of the code were necessary to be done in accordance with this task. The obtained results will be used for further sensitivity analysis Studies by using Monte Carlo simulation.

Nested parallelism for multi-core HPC systems using Java

Since its introduction in 1993, the Message Passing Interface (MPI) has become a de facto standard for writing High Performance Computing (HPC) applications on clusters and Massively Parallel Processors (MPPs). The recent emergence of multi-core processor systems presents a new challenge for established parallel programming paradigms, including those based on MPI. This paper presents a new Java messaging system called MPJ Express. Using this system, we exploit multiple levels of parallelism - messaging and threading - to improve application performance on multi-core processors. We refer to our approach as nested parallelism. This MPI-like Java library can support nested parallelism by using Java or Java OpenMP (JOMP) threads within an MPJ Express process. Practicality of this approach is assessed by porting to Java a massively parallel structure formation code from Cosmology called Gadget-2. We introduce nested parallelism in the Java version of the simulation code and report good speed-ups. To the best of our knowledge it is the first time this kind of hybrid parallelism is demonstrated in a high performance Java application. (C) 2009 Elsevier Inc. All rights reserved.

A comparative study of Java and C performance in two large-scale parallel applications

In the 1990s the Message Passing Interface Forum defined MPI bindings for Fortran, C, and C++. With the success of MPI these relatively conservative languages have continued to dominate in the parallel computing community. There are compelling arguments in favour of more modern languages like Java. These include portability, better runtime error checking, modularity, and multi-threading. But these arguments have not converted many HPC programmers, perhaps due to the scarcity of full-scale scientific Java codes, and the lack of evidence for performance competitive with C or Fortran. This paper tries to redress this situation by porting two scientific applications to Java. Both of these applications are parallelized using our thread-safe Java messaging system—MPJ Express. The first application is the Gadget-2 code, which is a massively parallel structure formation code for cosmological simulations. The second application uses the finite-domain time-difference method for simulations in the area of computational electromagnetics. We evaluate and compare the performance of the Java and C versions of these two scientific applications, and demonstrate that the Java codes can achieve performance comparable with legacy applications written in conventional HPC languages. Copyright © 2009 John Wiley & Sons, Ltd.

Multicore-enabling the MPJ express messaging library

With the transition to multicore processors almost complete, the parallel processing community is seeking efficient ways to port legacy message passing applications on shared memory and multicore processors. MPJ Express is our reference implementation of Message Passing Interface (MPI)-like bindings for the Java language. Starting with the current release, the MPJ Express software can be configured in two modes: the multicore and the cluster mode. In the multicore mode, parallel Java applications execute on shared memory or multicore processors. In the cluster mode, Java applications parallelized using MPJ Express can be executed on distributed memory platforms like compute clusters and clouds. The multicore device has been implemented using Java threads in order to satisfy two main design goals of portability and performance. We also discuss the challenges of integrating the multicore device in the MPJ Express software. This turned out to be a challenging task because the parallel application executes in a single JVM in the multicore mode. On the contrary in the cluster mode, the parallel user application executes in multiple JVMs. Due to these inherent architectural differences between the two modes, the MPJ Express runtime is modified to ensure correct semantics of the parallel program. Towards the end, we compare performance of MPJ Express (multicore mode) with other C and Java message passing libraries---including mpiJava, MPJ/Ibis, MPICH2, MPJ Express (cluster mode)---on shared memory and multicore processors. We found out that MPJ Express performs signicantly better in the multicore mode than in the cluster mode. Not only this but the MPJ Express software also performs better in comparison to other Java messaging libraries including mpiJava and MPJ/Ibis when used in the multicore mode on shared memory or multicore processors. We also demonstrate effectiveness of the MPJ Express multicore device in Gadget-2, which is a massively parallel astrophysics N-body siimulation code.

Handling single node failures using agents in computer clusters

The work reported in this paper is motivated towards handling single node failures for parallel summation algorithms in computer clusters. An agent based approach is proposed in which a task to be executed is decomposed to sub-tasks and mapped onto agents that traverse computing nodes. The agents intercommunicate across computing nodes to share information during the event of a predicted node failure. Two single node failure scenarios are considered. The Message Passing Interface is employed for implementing the proposed approach. Quantitative results obtained from experiments reveal that the agent based approach can handle failures more efficiently than traditional failure handling approaches.

Exploring carrier agents in swarm-array computing

How can a bridge be built between autonomic computing approaches and parallel computing systems? The work reported in this paper is motivated towards bridging this gap by proposing a swarm-array computing approach based on ‘Intelligent Agents’ to achieve autonomy for distributed parallel computing systems. In the proposed approach, a task to be executed on parallel computing cores is carried onto a computing core by carrier agents that can seamlessly transfer between processing cores in the event of a predicted failure. The cognitive capabilities of the carrier agents on a parallel processing core serves in achieving the self-ware objectives of autonomic computing, hence applying autonomic computing concepts for the benefit of parallel computing systems. The feasibility of the proposed approach is validated by simulation studies using a multi-agent simulator on an FPGA (Field-Programmable Gate Array) and experimental studies using MPI (Message Passing Interface) on a computer cluster. Preliminary results confirm that applying autonomic computing principles to parallel computing systems is beneficial.

An MPI-based implementation of intelligent agents on clusters

Recent research in multi-agent systems incorporate fault tolerance concepts, but does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely 'Intelligent Agents'. A task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The feasibility of the approach is validated by implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

Intelligent agents for fault tolerance: from multi-agent simulation to cluster-based implementation

Recent research in multi-agent systems incorporate fault tolerance concepts, but does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely 'Intelligent Agents'. A task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The feasibility of the approach is validated by simulations on an FPGA using a multi-agent simulator, and implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

A cluster-based implementation of a fault-tolerant parallel reduction algorithm using swarm-array computing

Recent research in multi-agent systems incorporate fault tolerance concepts. However, the research does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely ‘Intelligent Agents’. In the approach considered a task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The agents hence contribute towards fault tolerance and towards building reliable systems. The feasibility of the approach is validated by simulations on an FPGA using a multi-agent simulator and implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

A simple method for integrating a complex model into an ensemble data assimilation system using MPI

This paper details a strategy for modifying the source code of a complex model so that the model may be used in a data assimilation context, {and gives the standards for implementing a data assimilation code to use such a model}. The strategy relies on keeping the model separate from any data assimilation code, and coupling the two through the use of Message Passing Interface (MPI) {functionality}. This strategy limits the changes necessary to the model and as such is rapid to program, at the expense of ultimate performance. The implementation technique is applied in different models with state dimension up to $2.7 \times 10^8$. The overheads added by using this implementation strategy in a coupled ocean-atmosphere climate model are shown to be an order of magnitude smaller than the addition of correlated stochastic random errors necessary for some nonlinear data assimilation techniques.

Performance Improvement of Tomographic Image Reconstruction Based on DSP Processors

This paper presents the use of a multiprocessor architecture for the performance improvement of tomographic image reconstruction. Image reconstruction in computed tomography (CT) is an intensive task for single-processor systems. We investigate the filtered image reconstruction suitability based on DSPs organized for parallel processing and its comparison with the Message Passing Interface (MPI) library. The experimental results show that the speedups observed for both platforms were increased in the same direction of the image resolution. In addition, the execution time to communication time ratios (Rt/Rc) as a function of the sample size have shown a narrow variation for the DSP platform in comparison with the MPI platform, which indicates its better performance for parallel image reconstruction.