Dominik Meiländer

Parallel medical image reconstruction: from graphics processing units (GPU) to Grids

We present and compare a variety of parallelization approaches for a real-world case study on modern parallel and distributed computer architectures. Our case study is a production-quality, time-intensive algorithm for medical image reconstruction used in computer tomography (PET). We parallelize this algorithm for the main kinds of contemporary parallel architectures: shared-memory multiprocessors, distributed-memory clusters, graphics processing units (GPU) using the CUDA framework, the Cell processor and, finally, how various architectures can be accessed in a distributed Grid environment. The main contribution of the paper, besides the parallelization approaches, is their systematic comparison regarding four important criteria: performance, programming comfort, accessibility, and cost-effectiveness. We report results of experiments on particular parallel machines of different architectures that confirm the findings of our systematic comparison.

Bringing mobile online games to clouds

Massively Multi-player Online Games (MMOG) are characterized by intensive interactions between many simultaneous users and real-time demands on Quality of Service (QoS). Other examples of similar, real-time online interactive applications include various virtual environments, as well as multi-pupil e-learning and simulation-based training courses. A highly desirable enhancement for MMOG is the use of mobile devices for accessing the game application. However, the limited computing power of mobile devices is an obstacle for implementing computation-intensive parts of MMOG, in particular graphics processing, on mobile devices. This paper proposes a novel runtime system for mobile MMOG and other similar applications that moves computation-intensive tasks, including graphics processing, from the mobile devices to Cloud resources. We report experimental results of our runtime system using a realistic multi-player online game.

A dynamic resource management system for real-time online applications on clouds

We consider a challenging class of highly interactive virtual environments, also known as Real-Time Online Interactive Applications (ROIA). Popular examples of ROIA include multi-player online computer games, e-learning and training applications based on real-time simulations, etc. ROIA combine high demands on the scalability and real-time user interactivity with the problem of efficient and economic utilization of resources, which is difficult to achieve due to the changing number of users. We address these challenges by developing the dynamic resource management system RTF-RMS which implements load balancing for ROIA on Clouds. We illustrate how RTF-RMS chooses between three different load-balancing actions and implements Cloud resource allocation. We report experimental results on the load balancing of a multi-player online game in a Cloud environment using RTF-RMS.

Cost-effective medical image reconstruction: from clusters to graphics processing units

We demonstrate that for modern medical imaging applications, parallel implementations on traditional parallel architectures (clusters and multiprocessor servers) can be outperformed, both in terms of speed and cost-effectiveness, by new implementations on next-generation architectures like GPUs (Graphics Processing Units). Although, compared to clusters and multiprocessor servers, GPUs are rather small and much less expensive, they consist of several SIMD-processors and thus provide a high degree of parallelism. For an iterative image reconstruction algorithm---the list-mode OSEM--- we demonstrate, first, the limitations of parallel reconstructions with this algorithm on the traditional parallel architectures, and second, how the well-analyzed parallel strategies for traditional architectures can be adapted systematically to achieve fast reconstructions on the GPU.

Parallel Medical Image Reconstruction: From Graphics Processors to Grids

We present a variety of possible parallelization approaches for a real-world case study using several modern parallel and distributed computer architectures. Our case study is a production-quality, time-intensive algorithm for medical image reconstruction used in computer tomography. We describe how this algorithm can be parallelized for the main kinds of contemporary parallel architectures: shared-memory multiprocessors, distributed-memory clusters, graphics processors, the Cell processor and, finally, how various architectures can be accessed in a distributed Grid environment. The main contribution of the paper, besides the parallelization approaches, is their systematic comparison regarding four important criteria: performance, programming comfort, accessibility, and cost-effectiveness. We report results of experiments on particular parallel machines of different architectures that confirm the findings of our systematic comparison.

Using Mobile Cloud Computing for Real-Time Online Applications

We consider a challenging class of highly interactive virtual environments, also known as Real-Time Online Interactive Applications (ROIA). Popular examples of ROIA include multi-player online computer games, e-learning and training applications based on real-time simulations, among others. An emerging enhancement for ROIA is the use of mobile devices for accessing the application (mobile ROIA). However, the limited computing power of mobile devices is an obstacle for implementing computation-intensive parts of ROIA, in particular graphics processing, on mobile devices. This paper proposes a runtime system for mobile ROIA that moves computation-intensive tasks, including graphics processing, from the mobile devices to Cloud resources. We report experimental results of our runtime system using a multi-player online game with real-world characteristics.

Using a lifecycle model for developing and executing real-time online applications on clouds

We describe how the generic Lifecycle Model developed in the S-Cube project for the design and management of service-based applications (SBA) can be utilized in the context of Cloud Computing. In particular, we focus on the fact that the Infrastructure-as-a-Service approach enables the development of Real-Time Online Interactive Applications (ROIA), which include multi-player online computer games, interactive e-learning and training applications and high-performance simulations in virtual environments. We illustrate how the Lifecycle Model expresses the major design and execution aspects of ROIA on Clouds by addressing the specific characteristics of ROIA: a large number of concurrent users connected to a single application instance, enforcement of Quality of Service (QoS) parameters, adaptivity to changing loads, and frequent real-time interactions between users and services. We describe how our novel resource management system RTF-RMS implements concrete mechanisms that support the developer in designing adaptable ROIA on Clouds according to the different phases of the Lifecycle Model. Our experimental results demonstrate the influence of the proposed adaptation mechanisms on the application performance.

A Scalability Model for Distributed Resource Management in Real-Time Online Applications

We consider a challenging class of highly interactive virtual environments, also known as Real-Time Online Interactive Applications (ROIA). Popular examples of ROIA include multi-player online computer games, e-learning and training based on real-time simulations, and other challenging applications. ROIA combine high demands on scalability and real-time user interactivity with the problem of an efficient and economic utilization of resources, which is difficult to achieve due to the changing number of users. This paper proposes a generic scalability model for ROIA that analyzes the application performance during runtime and predicts the demand for load balancing, i.e., when to add/remove resources or redistribute workload. We prove the practical relevance of the model by incorporating it into our RTF-RMS resource management system where it is used to predict the influence of different load-balancing actions on the application scalability. Our model is utilized by RTF-RMS for finding efficient load-balancing actions and thresholds for how often these actions should be applied. We report experimental results on the load balancing of a multi-player online game using predictions from the scalability model.

Using a Lifecycle Model for Developing and Executing Adaptable Interactive Distributed Applications

We describe a case study on using the generic Lifecycle Model developed in the S-Cube project for a novel class of Real-time Online Interactive Applications (ROIA), which include distributed simulations (e.g. massively-multiplayer online games), e-learning and training. We describe how the Lifecycle Model supports application development by addressing the specific challenges of ROIA: a large number of concurrent users connected to a single application instance, frequent real-time user interactions, enforcement of Quality of Service (QoS) parameters, adaptivity to changing loads, and competition-oriented interaction between users, other actors, and services. We describe the implementation aspects of the application development and adaptation using the RTF (Real-Time Framework) middleware, and report experimental results for a sample online game application.

Modelling the Scalability of Real-Time Online Interactive Applications on Clouds

We address the scalability of Real-Time Online Interactive Applications (ROIA) on Clouds. Popular examples of ROIA include, e.g., multi-player online computer games, simulation-based e-learning, and training in real-time virtual environments. Cloud computing allows to combine ROIAs high demands on QoE (Quality of Experience) with the requirement of efficient and economic utilization of computation and network resources. We propose a generic scalability model for ROIA on Clouds that monitors the application performance at runtime and predicts the load-balancing decisions: by weighting the potential benefits of particular load-balancing actions against the time and resources overhead of them, our model recommends, whether and how often to redistribute workload or add/remove Cloud resources when the number of users changes. We describe how the scalability is modelled w.r.t. to two kinds of resources -- computation (CPU) and communication (network) -- and how we combine these models together. We experimentally evaluate the quality of our combined model using a challenging multi-player shooter game as a use case.