High-performance practical stiffness analysis of high-rise buildings using superfloor elements

Abstract

AbstractThis study develops a high-performance computing method using OpenACC (Open Accelerator) for the stiffness matrix and load vector generation of shear-deformable plates in bending using the boundary element method on parallel processors. The boundary element formulation for plates in bending is used to derive fully populated displacement-based stiffness matrices and load vectors at degrees of freedom of interest. The computed stiffness matrix of the plate is defined as a single superfloor element and can be solved using stiffness analysis, $Ku = F$, instead of the conventional boundary element method, $Hu = Gt$. Fortran OpenACC code implementations are proposed for the computation of the superfloor element’s stiffness, which includes one serial computing code for the CPU (central processing unit) and two parallel computing codes for the GPU (graphics processing unit) and multicore CPU. As industrial level practical floors are full of supports and geometrical information, the computation time of superfloor elements is reduced dramatically when computing on parallel processors. It is demonstrated that the OpenACC implementation does not affect numerical accuracy. The feasibility and accuracy are confirmed by numerical examples that include real buildings with industrial level structural floors. Engineering computations for massive floors with immense geometrical detail and a multitude of load cases can be modeled as is without the need for simplification.