Scope of MPI/OpenMP/CUDA parallelization of harmonic coupled finite strip method applied on large displacement stability analysis of prismatic shell structures | Zendy

M. Hajdukovic | Zendy; Dragan D. Milašinović | Zendy; Milan P. Nikolić | Zendy; Predrag Rakić | Zendy; Žarko Živanov | Zendy; Lazar Stričević | Zendy

Open Access

Scope of MPI/OpenMP/CUDA parallelization of harmonic coupled finite strip method applied on large displacement stability analysis of prismatic shell structures

Author(s) -

M. Hajdukovic,

Dragan D. Milašinović,

Milan P. Nikolić,

Predrag Rakić,

Žarko Živanov,

Lazar Stričević

Publication year - 2012

Publication title -

computer science and information systems

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.244

H-Index - 24

eISSN - 2406-1018

pISSN - 1820-0214

DOI - 10.2298/csis110822011h

Subject(s) - computer science , computation , cuda , parallel computing , boundary value problem , orthotropic material , computational science , displacement (psychology) , series (stratigraphy) , algorithm , finite element method , structural engineering , mathematics , mathematical analysis , psychology , paleontology , engineering , psychotherapist , biology

This paper presents scope of parallelization in large displacement stability analysis of orthotropic prismatic shells with simply supported boundary conditions along the diaphragm-supported edges. A semi-analytical harmonic coupled finite strip method (HCFSM) is used to solve the large deflection and the post-buckling problems. In the HCFSM formulation the coupling of all series terms highly increases computation time when a large number of series terms is used. Fortunately such computation time increase can be compensated by application of MPI, OpenMP and CUDA approaches to parallelization. This paper shows how these approaches can be applied to HCFSM formulation, and what results can be expected.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research