@article{AlhaddadFoerstnerGrothetal., author = {Alhaddad, Samer and F{\"o}rstner, Jens and Groth, Stefan and Gr{\"u}newald, Daniel and Grynko, Yevgen and Hannig, Frank and Kenter, Tobias and Pfreundt, F.J. and Plessl, Christian and Schotte, Merlind and Steinke, Thomas and Teich, J. and Weiser, Martin and Wende, Florian}, title = {The HighPerMeshes Framework for Numerical Algorithms on Unstructured Grids}, series = {Concurrency and Computation: Practice and Experience}, volume = {34}, journal = {Concurrency and Computation: Practice and Experience}, number = {14}, doi = {10.1002/cpe.6616}, abstract = {Solving PDEs on unstructured grids is a cornerstone of engineering and scientific computing. Heterogeneous parallel platforms, including CPUs, GPUs, and FPGAs, enable energy-efficient and computationally demanding simulations. In this article, we introduce the HPM C++-embedded DSL that bridges the abstraction gap between the mathematical formulation of mesh-based algorithms for PDE problems on the one hand and an increasing number of heterogeneous platforms with their different programming models on the other hand. Thus, the HPM DSL aims at higher productivity in the code development process for multiple target platforms. We introduce the concepts as well as the basic structure of the HPM DSL, and demonstrate its usage with three examples. The mapping of the abstract algorithmic description onto parallel hardware, including distributed memory compute clusters, is presented. A code generator and a matching back end allow the acceleration of HPM code with GPUs. Finally, the achievable performance and scalability are demonstrated for different example problems.}, language = {en} } @misc{NoackWendeZitzlsbergeretal., author = {Noack, Matthias and Wende, Florian and Zitzlsberger, Georg and Klemm, Michael and Steinke, Thomas}, title = {KART - A Runtime Compilation Library for Improving HPC Application Performance}, issn = {1438-0064}, doi = {10.1007/978-3-319-67630-2_29}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-60730}, abstract = {The effectiveness of ahead-of-time compiler optimization heavily depends on the amount of available information at compile time. Input-specific information that is only available at runtime cannot be used, although it often determines loop counts, branching predicates and paths, as well as memory-access patterns. It can also be crucial for generating efficient SIMD-vectorized code. This is especially relevant for the many-core architectures paving the way to exascale computing, which are more sensitive to code-optimization. We explore the design-space for using input-specific information at compile-time and present KART, a C++ library solution that allows developers to compile, link, and execute code (e.g., C, C++ , Fortran) at application runtime. Besides mere runtime compilation of performance-critical code, KART can be used to instantiate the same code multiple times using different inputs, compilers, and options. Other techniques like auto-tuning and code-generation can be integrated into a KART-enabled application instead of being scripted around it. We evaluate runtimes and compilation costs for different synthetic kernels, and show the effectiveness for two real-world applications, HEOM and a WSM6 proxy.}, language = {en} } @inproceedings{NoackWendeSteinkeetal., 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}, series = {SC '14: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. SC14, November 16-21, 2014, New Orleans, Louisiana, USA}, 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}, 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} } @inproceedings{WendeSteinkeReinefeld, author = {Wende, Florian and Steinke, Thomas and Reinefeld, Alexander}, title = {The Impact of Process Placement and Oversubscription on Application Performance: A Case Study for Exascale Computing}, series = {Proceedings of the 3rd International Conference on Exascale Applications and Software, EASC 2015}, booktitle = {Proceedings of the 3rd International Conference on Exascale Applications and Software, EASC 2015}, editor = {Gray, A. and Smith, L. and Weiland, M.}, publisher = {The University of Edinburgh}, isbn = {978 -0-9 926615 -1-9}, pages = {13 -- 18}, language = {en} } @inproceedings{WendeCordesSteinke, author = {Wende, Florian and Cordes, Frank and Steinke, Thomas}, title = {Concurrent Kernel Execution on Xeon Phi within Parallel Heterogeneous Workloads}, series = {Euro-Par 2014: Parallel Processing. 20th International Conference, Porto, Portugal, August 25-29, 2014, Proceedings}, 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}, language = {en} } @inproceedings{WendeSteinke, author = {Wende, Florian and Steinke, Thomas}, title = {Swendsen-Wang Multi-Cluster Algorithm for the 2D/3D Ising Model on Xeon Phi and GPU}, series = {Proceeding SC '13 Proceedings of SC13: International Conference for High Performance Computing, Networking, Storage and Analysis Article No. 83 ACM New York, NY, USA, 2013}, booktitle = {Proceeding SC '13 Proceedings of SC13: International Conference for High Performance Computing, Networking, Storage and Analysis Article No. 83 ACM New York, NY, USA, 2013}, doi = {http://dx.doi.org/10.1145/2503210.2503254}, language = {en} } @inproceedings{WendeLaubenderSteinke, author = {Wende, Florian and Laubender, Guido and Steinke, Thomas}, title = {Integration of Intel Xeon Phi Servers into the HLRN-III Complex: Experiences, Performance and Lessons Learned}, series = {CUG2014 Proceedings}, booktitle = {CUG2014 Proceedings}, language = {en} } @misc{WendeSteinkeKlemmetal., author = {Wende, Florian and Steinke, Thomas and Klemm, Michael and Reinefeld, Alexander}, title = {Concurrent Kernel Offloading}, series = {High Performance Parallelism Pearls}, journal = {High Performance Parallelism Pearls}, editor = {Reinders, James and Jeffers, Jim}, publisher = {Morgan Kaufman, Elsevier}, isbn = {978-0128021187}, language = {en} } @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}, series = {Application Accelerators in High Performance Computing (SAAHPC), 2012 Symposium on}, booktitle = {Application Accelerators in High Performance Computing (SAAHPC), 2012 Symposium on}, doi = {10.1109/SAAHPC.2012.12}, pages = {74 -- 83}, year = {2012}, language = {en} } @incollection{NoackWendeZitzlsbergeretal., author = {Noack, Matthias and Wende, Florian and Zitzlsberger, Georg and Klemm, Michael and Steinke, Thomas}, title = {KART - A Runtime Compilation Library for Improving HPC Application Performance}, series = {High Performance Computing: ISC High Performance 2017 International Workshops, DRBSD, ExaComm, HCPM, HPC-IODC, IWOPH, IXPUG, P^3MA, VHPC, Visualization at Scale, WOPSSS, Frankfurt, Germany, June 18-22, 2017, Revised Selected Papers}, volume = {10524}, booktitle = {High Performance Computing: ISC High Performance 2017 International Workshops, DRBSD, ExaComm, HCPM, HPC-IODC, IWOPH, IXPUG, P^3MA, VHPC, Visualization at Scale, WOPSSS, Frankfurt, Germany, June 18-22, 2017, Revised Selected Papers}, publisher = {Springer International Publishing}, doi = {10.1007/978-3-319-67630-2_29}, pages = {389 -- 403}, abstract = {The effectiveness of ahead-of-time compiler optimization heavily depends on the amount of available information at compile time. Input-specific information that is only available at runtime cannot be used, although it often determines loop counts, branching predicates and paths, as well as memory-access patterns. It can also be crucial for generating efficient SIMD-vectorized code. This is especially relevant for the many-core architectures paving the way to exascale computing, which are more sensitive to code-optimization. We explore the design-space for using input-specific information at compile-time and present KART, a C++ library solution that allows developers tocompile, link, and execute code (e.g., C, C++ , Fortran) at application runtime. Besides mere runtime compilation of performance-critical code, KART can be used to instantiate the same code multiple times using different inputs, compilers, and options. Other techniques like auto-tuning and code-generation can be integrated into a KART-enabled application instead of being scripted around it. We evaluate runtimes and compilation costs for different synthetic kernels, and show the effectiveness for two real-world applications, HEOM and a WSM6 proxy.}, language = {en} }