@inproceedings{WendeCordesSteinke2012, author = {Wende, Florian and Cordes, Frank and Steinke, Thomas}, title = {On Improving the Performance of Multi-threaded CUDA Applications with Concurrent Kernel Execution by Kernel Reordering}, booktitle = {Application Accelerators in High Performance Computing (SAAHPC), 2012 Symposium on}, doi = {10.1109/SAAHPC.2012.12}, pages = {74 -- 83}, year = {2012}, language = {en} } @inproceedings{GalliatDeuflhardRoitzschetal.2002, author = {Galliat, Tobias and Deuflhard, Peter and Roitzsch, Rainer and Cordes, Frank}, title = {Automatic Identification of Metastable Conformations via Self-Organized Neural Networks}, booktitle = {Computational Methods for Macromolecules}, number = {24}, editor = {Schlick, T. and Gan, H.}, publisher = {Springer}, year = {2002}, language = {en} } @inproceedings{GalliatDeuflhardRoitzschetal.2002, author = {Galliat, Tobias and Deuflhard, Peter and Roitzsch, Rainer and Cordes, Frank}, title = {Automatic identification of metastable conformations via self-organized neural networks}, booktitle = {Proceedings of the 3rd International Workshop on Algorithms for Macromolecular Modelling}, year = {2002}, language = {en} } @inproceedings{FischerSchuetteDeuflhardetal.2002, author = {Fischer, Alexander and Sch{\"u}tte, Christof and Deuflhard, Peter and Cordes, Frank}, title = {Hierarchical Uncoupling-Coupling of Metastable Conformations}, booktitle = {Computational Methods for Macromolecules}, number = {24}, editor = {Schlick, T. and Gan, H.}, publisher = {Springer}, pages = {235 -- 259}, year = {2002}, language = {en} } @inproceedings{SchuetteCordes2000, author = {Sch{\"u}tte, Christof and Cordes, Frank}, title = {On Dynamical Transitions between Conformational Ensembles}, booktitle = {Molecular Dynamics on Parallel Computers}, editor = {Esser, R. and Grassberger, P. and Grotendorst, J. and Lewerenz, M.}, publisher = {World Scientific}, doi = {10.1142/9789812793768_0002}, pages = {32 -- 45}, year = {2000}, language = {en} } @inproceedings{FischerSchuetteDeuflhardetal.2002, author = {Fischer, Alexander and Sch{\"u}tte, Christof and Deuflhard, Peter and Cordes, Frank}, title = {Hierarchical Uncoupling-Coupling of Metastable Conformations}, volume = {24}, booktitle = {Computational Methods for Macromolecules}, editor = {Schlick, T. and Gan, H.}, publisher = {Springer}, pages = {235 -- 259}, year = {2002}, language = {en} } @inproceedings{WendeCordesSteinke2014, author = {Wende, Florian and Cordes, Frank and Steinke, Thomas}, title = {Concurrent Kernel Execution on Xeon Phi within Parallel Heterogeneous Workloads}, volume = {8632}, booktitle = {Euro-Par 2014: Parallel Processing. 20th International Conference, Porto, Portugal, August 25-29, 2014, Proceedings}, doi = {10.1007/978-3-319-09873-9_66}, pages = {788 -- 799}, year = {2014}, language = {en} } @inproceedings{NoackWendeSteinkeetal.2014, author = {Noack, Matthias and Wende, Florian and Steinke, Thomas and Cordes, Frank}, title = {A Unified Programming Model for Intra- and Inter-Node Offloading on Xeon Phi Clusters}, booktitle = {SC '14: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. SC14, November 16-21, 2014, New Orleans, Louisiana, USA}, doi = {10.1109/SC.2014.22}, year = {2014}, abstract = {Standard offload programming models for the Xeon Phi, e.g. Intel LEO and OpenMP 4.0, are restricted to a single compute node and hence a limited number of coprocessors. Scaling applications across a Xeon Phi cluster/supercomputer thus requires hybrid programming approaches, usually MPI+X. In this work, we present a framework based on heterogeneous active messages (HAM-Offload) that provides the means to offload work to local and remote (co)processors using a unified offload API. Since HAM-Offload provides similar primitives as current local offload frameworks, existing applications can be easily ported to overcome the single-node limitation while keeping the convenient offload programming model. We demonstrate the effectiveness of the framework by using it to enable a real-world application from the field of molecular dynamics to use multiple local and remote Xeon Phis. The evaluation shows good scaling behavior. Compared with LEO, performance is equal for large offloads and significantly better for small offloads.}, language = {en} }