top
The presented contribution maps the possibilities of exploitation of the massive parallel computational hardware (namely GPU) for solution of the initial value problems of ordinary differential equations. Two cases are discussed: parallel solution of a single ODE and parallel execution of scalar ODE solvers. Whereas the advantages of the special architecture in the case of a single ODE are problematic, repeated solution of a single ODE for different data can profit from the parallel architecture. However, special algorithms have to be used even in the latter case to avoid code divergence between individual computational threads. The topic is illustrated on several examples.
Fischer, Cyril. "Massive parallel implementation of ODE solvers." Programs and Algorithms of Numerical Mathematics. Prague: Institute of Mathematics AS CR, 2013. 75-80. <http://eudml.org/doc/271400>.
@inProceedings{Fischer2013, abstract = {The presented contribution maps the possibilities of exploitation of the massive parallel computational hardware (namely GPU) for solution of the initial value problems of ordinary differential equations. Two cases are discussed: parallel solution of a single ODE and parallel execution of scalar ODE solvers. Whereas the advantages of the special architecture in the case of a single ODE are problematic, repeated solution of a single ODE for different data can profit from the parallel architecture. However, special algorithms have to be used even in the latter case to avoid code divergence between individual computational threads. The topic is illustrated on several examples.}, author = {Fischer, Cyril}, booktitle = {Programs and Algorithms of Numerical Mathematics}, keywords = {CUDA; GPU; CULSODA; ODEINT; initial value problems for ODE; response spectra; resonance curve}, location = {Prague}, pages = {75-80}, publisher = {Institute of Mathematics AS CR}, title = {Massive parallel implementation of ODE solvers}, url = {http://eudml.org/doc/271400}, year = {2013}, }
TY - CLSWK AU - Fischer, Cyril TI - Massive parallel implementation of ODE solvers T2 - Programs and Algorithms of Numerical Mathematics PY - 2013 CY - Prague PB - Institute of Mathematics AS CR SP - 75 EP - 80 AB - The presented contribution maps the possibilities of exploitation of the massive parallel computational hardware (namely GPU) for solution of the initial value problems of ordinary differential equations. Two cases are discussed: parallel solution of a single ODE and parallel execution of scalar ODE solvers. Whereas the advantages of the special architecture in the case of a single ODE are problematic, repeated solution of a single ODE for different data can profit from the parallel architecture. However, special algorithms have to be used even in the latter case to avoid code divergence between individual computational threads. The topic is illustrated on several examples. KW - CUDA; GPU; CULSODA; ODEINT; initial value problems for ODE; response spectra; resonance curve UR - http://eudml.org/doc/271400 ER -