Výsledky vyhledávání

Intel Xeon Phi acceleration of Hybrid Total FETI solver

Autor: Alexandros Markopoulos, Lubomir Riha, Vít Vondrák, Tomas Brzobohaty, Tomáš Kozubek, Ondrej Meca, Michal Merta

Publikováno v: Advances in Engineering Software. 112:124-135

This paper describes an approach for acceleration of the Hybrid Total FETI (HTFETI) domain decomposition method using the Intel Xeon Phi coprocessors. The HTFETI method is a memory bound algorithm which uses sparse linear BLAS operations with irregul

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::932e4c32aa531a93a655cf73eb48a794
https://doi.org/10.1016/j.advengsoft.2017.05.001

Zobrazit plný text záznamu

An Approach for Parallel Loading and Pre-Processing of Unstructured Meshes Stored in Spatially Scattered Fashion

Autor: Ondrej Meca, Lubomir Riha, Tomas Brzobohaty

Publikováno v: IPDPS

This paper presents a workflow for parallel loading of database files containing sequentially stored unstructured meshes that are not considered to be efficiently read in parallel. In such a file consecutive elements are not spatially located and the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d9704a888e2c0132a133373ad64afd88
https://doi.org/10.1109/ipdps.2019.00084

Zobrazit plný text záznamu

An automatically generated graphical configuration tool for the massively parallel library ESPRESO

Autor: Tomas Brzobohaty, Lukas Maly, Lubomir Riha, Ondrej Meca, Tomas Panoc

Publikováno v: AIP Conference Proceedings.

This paper presents a graphical configuration tool for the massively parallel FETI solver implemented in the open source library ESPRESO. The main aim of this tool is to simplify and speed up the configuration process, which is currently performed by

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a9baf04691fee7759eaf5da41cd1995d
https://doi.org/10.1063/1.5114334

Zobrazit plný text záznamu

An Approach to Verification of MPI Applications Defined in a High-Level Model

Autor: Ondrej Meca, Marek Behaleky, Stanislav Bohm, Petr Jancary

Publikováno v: ACSD

Kaira is a prototyping tool for developing MPI programs (Bohm et al., Petri Nets 2014). The user of Kaira suggests a parallelization of a given sequential C++ code by creating a visual Petri-net based model, the tool then automatically generates the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d8e837475d09f0fddf7f33f8006b9550
https://doi.org/10.1109/acsd.2016.17

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání