000014828 001__ 14828 000014828 005__ 20161115100203.0 000014828 04107 $$aeng 000014828 046__ $$k2016-08-21 000014828 100__ $$aAdams, Darren 000014828 24500 $$aPetascale DNS using the fast Poisson solver PSH3D 000014828 24630 $$n24.$$p24th International Congress of Theoretical and Applied Mechanics - Book of Papers 000014828 260__ $$bInternational Union of Theoretical and Applied Mechanics, 2016 000014828 506__ $$arestricted 000014828 520__ $$2eng$$aDirect numerical simulation (DNS) of high Reynolds number (Re = O(105 )) turbulent flows requires computational meshes of O(1012 ) grid points. Thus, DNS requires the use of petascale supercomputers. DNS often requires the solution of a Helmholtz (or Poisson) equation for pressure, which constitutes the bottleneck of the solver. We have developed and implemented a parallel solver of the Helmholtz equation in 3D called petascale Helmholtz 3D (PSH3D). The numerical method underlying PSH3D combines a parallel 2D Fast Fourier transform (P2DFFT) and a parallel linear solver (PLS). Our numerical results show that PSH3D scales up to at least 262,144 cores. PSH3D has a peak performance 6× faster than 3D FFT-based methods (e.g., P3DFFT) when used with the partial-global optimization. We have verified that the use of PSH3D with the partial-global optimization in our DNS solver does not reduce the accuracy of the numerical solution when tested for the Taylor-Green vortex flow. 000014828 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb. 000014828 653__ $$a 000014828 7112_ $$a24th International Congress of Theoretical and Applied Mechanics$$cMontreal (CA)$$d2016-08-21 / 2016-08-26$$gICTAM2016 000014828 720__ $$aAdams, Darren 000014828 8560_ $$ffischerc@itam.cas.cz 000014828 8564_ $$s117529$$uhttps://invenio.itam.cas.cz/record/14828/files/TS.FS02-2.04.pdf$$yOriginal version of the author's contribution as presented on CD, page 3111, code TS.FS02-2.04 . 000014828 962__ $$r13812 000014828 980__ $$aPAPER