@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} } @misc{Noack, author = {Noack, Matthias}, title = {HAM - Heterogenous Active Messages for Efficient Offloading on the Intel Xeon Phi}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-50610}, abstract = {The applicability of accelerators is limited by the attainable speed-up for the offloaded computations and by the offloading overheads. While GPU programming models like CUDA and OpenCL only allow to optimise the application code and its speed-up, the available low-level APIs for the Intel Xeon Phi provide opportunity to address the overheads, too. This work presents an Heterogeneous Active Message (HAM) layer that minimises software overheads for offloading on Intel's Xeon Phi. It provides the basis for an offload API with similar semantics as the Intel Language Extensions for Offload (LEO). In contrast to LEO, HAM works within the C++ language and needs no additional compiler support. We evaluated HAM on top of SCIF and MPI as communication backends. While the SCIF backend offers the best performance, the MPI backend allows for inter-node offloads which are not possible with other offload solutions. Benchmark results show that the cost for offloading a function call can be decreased by a factor up to 18 compared with LEO.}, language = {en} }