We provide details on the shared-memory parallelization for manycore architectures of the molecular dynamics framework ls1-mardyn, including an optimization of the SIMD vectorization for multi-centered molecules. The novel shared-memory parallelization scheme allows to retain Newton's third law optimization and exhibits very good scaling on many-core devices such as a full Xeon Phi card running 240 threads. The Xeon Phi can thus be exploited and delivers comparable performance as IvyBridge nodes in our experiments.
@inproceedings{OFCIMDSFTI15, author = {Nikola Tchipev and Amer Wafai and Colin W. Glass and Wolfgang Eckhardt and Alexander Heinecke and Hans-Joachim Bungartz and Philipp Neumann}, title = {{Optimized Force Calculation in Molecular Dynamics Simulations for the Intel Xeon Phi}}, year = {2015}, booktitle = {{Euro-Par 2015: Parallel Processing Workshops}}, publisher = {Springer}, address = {Berlin, Heidelberg}, series = {Lecture Notes in Computer Science}, number = {9523}, pages = {774--785}, conference = {Euro-Par 2015}, location = {Vienna}, isbn = {978-3-319-27307-5}, doi = {http://dx.doi.org/10.1007/978-3-319-27308-2_62}, abstract = {We provide details on the shared-memory parallelization for manycore architectures of the molecular dynamics framework ls1-mardyn, including an optimization of the SIMD vectorization for multi-centered molecules. The novel shared-memory parallelization scheme allows to retain Newton's third law optimization and exhibits very good scaling on many-core devices such as a full Xeon Phi card running 240 threads. The Xeon Phi can thus be exploited and delivers comparable performance as IvyBridge nodes in our experiments.}, }