Ethem Arkin

Model-Driven Approach for Supporting the Mapping of Parallel Algorithms to Parallel Computing Platforms

The trend from single processor to parallel computer architectures has increased the importance of parallel computing. To support parallel computing it is important to map parallel algorithms to a computing platform that consists of multiple parallel processing nodes. In general different alternative mappings can be defined that perform differently with respect to the quality requirements for power consumption, efficiency and memory usage. The mapping process can be carried out manually for platforms with a limited number of processing nodes. However, for exascale computing in which hundreds of thousands of processing nodes are applied, the mapping process soon becomes intractable. To assist the parallel computing engineer we provide a model-driven approach to analyze, model, and select feasible mappings. We describe the developed toolset that implements the corresponding approach together with the required metamodels and model transformations. We illustrate our approach for the well-known complete exchange algorithm in parallel computing.

Architecture framework for modeling the deployment of parallel applications on parallel computing platforms

To increase the computing performance the current trend is towards applying parallel computing in which the tasks are run in parallel on multiple nodes. Current approaches in parallel computing tend to focus on mapping parallel algorithms to parallel computing platforms. However, the complexity and variety of current software systems goes beyond the notion of algorithms only, and needs to consider the design from a broader application perspective that requires explicit design abstractions. For this purpose, we propose an architecture framework for modeling parallel applications to support the communication among the stakeholders, to reason about the design decisions and to support the analysis of the architectural design. The architecture framework consists of six coherent set of viewpoints which addresses different concerns in the design of parallel applications. The architecture framework is based on a metamodel that is derived after a thorough domain analysis on parallel computing. To support the architecture design process we have also developed the corresponding tool set that implements the architecture framework. The application of the architecture framework is illustrated for an order management application.

Domain Specific Language for Deployment of Parallel Applications on Parallel Computing Platforms

To increase the computing performance the current trend is towards applying parallel computing in which parallel tasks are executed on multiple nodes. The deployment of tasks on the computing platform usually impacts the overall performance and as such needs to be modelled carefully. In the architecture design community the deployment viewpoint is an important viewpoint to support this mapping process. In general the derived deployment views are visual notations that are not amenable for run-time processing, and do not scale well for deployment of large scale parallel applications. In this paper we propose a domain specific language (DSL) for modeling the deployment of parallel applications and for providing automated support for the deployment process. The DSL is based on a metamodel that is derived after a domain analysis on parallel computing. We illustrate the application of the DSL for a traffic simulation system and provide a set of important scenarios for using the DSL.

Architectural view driven model transformations for supporting the lifecycle of parallel applications

Two important trends can be identified in parallel computing. First of all, the scale of parallel computing platforms is rapidly increasing. Secondly, the complexity and variety of current software systems requires to consider the parallelization of application modules beyond algorithms. These two trends have led to a complexity that is not scalable and tractable anymore for manual processing, and therefore automated support is required to design and implement parallel applications. In this context, we present a model-driven transformation chain for supporting the automation of the lifecycle of parallel computing applications. The model-driven transformation chain adopts metamodels that are derived from architectural viewpoints. The transformation chain is defined as a logical sequence consisting of model-to-model transformations. We present the tool support that implements the metamodels and transformations.

Parallel Application Development Using Architecture View Driven Model Transformations

To realize the increased need for computing performance the current trend is towards applying parallel computing in which the tasks are run in parallel on multiple nodes. On its turn we can observe the rapid increase of the scale of parallel computing platforms. This situation has led to a complexity of parallel application development that is not scalable and tractable anymore for manual processing, and therefore automated support is required to design and implement parallel applications. To this end, we present a model-driven transformation chain for supporting the automation of the lifecycle of parallel computing applications. The model-driven transformation chain adopts metamodels that are derived from architecture viewpoints. The transformation chain is defined as a logical sequence consisting of model-to-model transformations. We present the tool support that implements the metamodels and transformations.

Systematic approach for deriving feasible mappings of parallel algorithms to parallel computing platforms

The need for high‐performance computing together with the increasing trend from single processor to parallel computer architectures has leveraged the adoption of parallel computing. To benefit from parallel computing power, usually parallel algorithms are defined that can be mapped and executed on parallel computing platforms. In general, different alternative mappings can be defined each with different performance. For small computing platforms with a limited number of processing nodes, the mapping process can be carried out manually. However, for large‐scale parallel computing platforms in which hundreds of thousands of processing nodes are applied, the number of possible mapping alternatives increases dramatically, and the mapping process becomes intractable for the human engineer. To assist the parallel computing engineer, we provide a systematic approach to derive feasible mapping alternatives of parallel algorithms to parallel computing platforms. The approach includes activities for modeling the parallel algorithm and parallel computing platform, generation of feasible mapping alternatives, generation of the deployment code, and finally the deployment of the generated code to the nodes. We evaluate our approach for deriving feasible mapping alternatives for four well‐known parallel algorithms. The evaluation is based on both simulations and real executions of the generated mapping alternatives. Copyright

Model-driven product line engineering for mapping parallel algorithms to parallel computing platforms

Mapping parallel algorithms to parallel computing platforms requires several activities such as the analysis of the parallel algorithm, the definition of the logical configuration of the platform, the mapping of the algorithm to the logical configuration platform and the implementation of the source code. Applying this process from scratch for each parallel algorithm is usually time consuming and cumbersome. Moreover, for large platforms this overall process becomes intractable for the human engineer. To support systematic reuse we propose to adopt a model-driven product line engineering approach for mapping parallel algorithms to parallel computing platforms. Using model-driven transformation patterns we support the generation of logical configurations of the computing platform and the generation of the parallel source code that runs on the parallel computing platform nodes. The overall approach is illustrated for mapping an example parallel algorithm to parallel computing platforms.

A threat evaluation model for small-scale naval platforms with limited capability

Naval command and control (C2) systems guide the operators to fulfill combat actions under time-constrained circumstances. Selecting proper targets among hundreds is an important decision making process with no compensation. Hereby, threat evaluation is a critical fusion operation to accelerate this process and increase situational awareness level in military domain services. However, combat management system could suffer from small-scale platforms supplying insufficient inputs that allow only limited foresight of common tactical picture. In this paper we present an experience on deriving threat evaluation value by pruning general approaches to meet operational needs of small-scale naval platforms along decision making process. We represent a method to obtain tactical information from only kinematics of target in two dimensional space. In the meanwhile, there is no knowledge about characteristics and identification of target which are strategically very important. Threat evaluation model is composed of the extraction of threat assessment cues, threat selection step supported by Bayesian Inference and the calculation of threat assessment rating. We have analyzed performance of proposed threat evaluation model simulating a set of synthetic scenarios and observed real-life results on functioning naval platform.