A5024382626- Parallel Computing and Optimization Techniques
- Distributed and Parallel Computing Systems
- Cloud Computing and Resource Management
- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- Explainable Artificial Intelligence (XAI)
- Ethics and Social Impacts of AI
- Artificial Intelligence in Healthcare and Education
- Advanced Multi-Objective Optimization Algorithms
- Graph Theory and Algorithms
- Gender and Technology in Education
- Business Process Modeling and Analysis
- Model-Driven Software Engineering Techniques
- Software Testing and Debugging Techniques
- Algorithms and Data Compression
- Management and Marketing Education
- Education, Achievement, and Giftedness
Association for Computing Machinery
2020
University of Münster
2016-2019
European Research Center for Information Systems
2018-2019
Parallel programming for an infrastructure of multi-core or many-core clusters is a challenge developers without experience in this domain. Developers need to use several libraries such as MPI, OpenMP, and CUDA efficiently the hardware which may include additional accelerators GPUs. Also, performing low-level optimizations required order reach high performance. One approach overcome these issues concept Algorithmic Skeletons. These are instances typical patterns parallel programming, map,...
The demand for computational power is constantly increasing, which requires financial investments and know-how companies. answer to this challenge two-fold. First, companies can rely on cloud providers provide infrastructure. Second, programming models emerged simplify parallel programming, one of them being algorithmic skeletons. In paper, we propose an efficient way deploy applications using the C++ skeleton library Muesli in a environment by Docker tools abstraction automatic node...
Swarm intelligence (SI) algorithms are handy tools for solving complex optimization problems. When problems grow in size and complexity, an increase population or number of iterations might be required order to achieve a good solution. These adjustments also impact the execution time. This article investigates trade-off involving size, problem aiming improve efficiency SI algorithms. Results based on parallel implementation Fish School Search show that increasing is beneficial finding...
Abstract In earlier work, we defined a domain-specific language (DSL) with the aim to provide an easy-to-use approach for programming multi-core and multi-GPU clusters. The DSL incorporates idea of utilizing algorithmic skeletons, which are well-known patterns parallel programming, such as map reduce. Based on chosen skeleton, user-defined function can be applied data structure in main advantage that user does not have worry about implementation details. So far, had only implemented...
Swarm Intelligence (SI) algorithms, such as Fish School Search (FSS), are well known useful tools that can be used to achieve a good solution in reasonable amount of time for complex optimization problems. And when problems increase size and complexity, some population or number iterations might needed order solution. In extreme cases, the execution huge other approaches, parallel implementations, help reduce it. This paper investigates relation trade off involving these three aspects SI...
Algorithmic systems are increasingly deployed to make decisions in many areas of people's lives. The shift from human algorithmic decision-making has been accompanied by concern about potentially opaque that not aligned with social values, as well proposed remedies such explainability. We present results a qualitative study decision-making, comprised five workshops conducted total 60 participants Finland, Germany, the United Kingdom, and States. invited reason qualities explainability...