@inproceedings{HandmannKopinskiMalysiak2015,
  author    = {Uwe Handmann and Thomas Kopinski and Darius Malysiak},
  title     = {A generic and adaptive approach for workload distribution in multitier cluster systems with an application to distributed matrix multiplication},
  series = {In 16th IEEE International Symposium on Computational Intelligence and Informatics, Budapest, Hungary},
  year      = {2015},
  abstract  = {We present a novel approach of distributing matrix multiplications among GPU-equipped nodes in a cluster system. In this context we discuss the induced challenges and possible solutions. Additionally we state an algorithm which outperforms optimized GPU BLAS libraries for small matrices. Furthermore we provide a novel theoretical model for distributing algorithms within homogeneous computation systems with multiple hierarchies. In the context of this model we develop an algorithm which can find the optimal distribution parameters for each involved subalgorithm. We provide a detailed analysis of the algorithms space and time complexities and justify its use with a structured evaluation within a small GPU-equipped Beowulf cluster.},
  language  = {en}
}