@conference {841, title = {Hierarchical DAG scheduling for Hybrid Distributed Systems}, booktitle = {29th IEEE International Parallel \& Distributed Processing Symposium (IPDPS)}, year = {2015}, month = {2015-05}, publisher = {IEEE}, organization = {IEEE}, address = {Hyderabad, India}, abstract = {Accelerator-enhanced computing platforms have drawn a lot of attention due to their massive peak com-putational capacity. Despite significant advances in the pro-gramming interfaces to such hybrid architectures, traditional programming paradigms struggle mapping the resulting multi-dimensional heterogeneity and the expression of algorithm parallelism, resulting in sub-optimal effective performance. Task-based programming paradigms have the capability to alleviate some of the programming challenges on distributed hybrid many-core architectures. In this paper we take this concept a step further by showing that the potential of task-based programming paradigms can be greatly increased with minimal modification of the underlying runtime combined with the right algorithmic changes. We propose two novel recursive algorithmic variants for one-sided factorizations and describe the changes to the PaRSEC task-scheduling runtime to build a framework where the task granularity is dynamically adjusted to adapt the degree of available parallelism and kernel effi-ciency according to runtime conditions. Based on an extensive set of results we show that, with one-sided factorizations, i.e. Cholesky and QR, a carefully written algorithm, supported by an adaptive tasks-based runtime, is capable of reaching a degree of performance and scalability never achieved before in distributed hybrid environments. }, keywords = {dense linear algebra, gpu, heterogeneous architecture, PaRSEC runtime}, author = {Wei Wu and Aurelien Bouteiller and George Bosilca and Mathieu Faverge and Jack Dongarra} }