• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.87-94
• /
• 2020

Recently, computer hardware is evolving toward increasing the number of computing cores, not increasing the clock speed. In order to use the performance of parallelized hardware to the maximum, the running program must also be parallelized. However, software developers are accustomed to sequential programs, and in most cases, write programs that operate sequentially. They also have a lot of difficulty designing and developing software in parallel. We propose a method to automatically convert a sequential C/C++ program into a parallelized program, and develop a parallelization tool that supports it. It supports open multiprocessing (OpenMP) and parallel patterns library (PPL) as a parallel framework. Perfect automatic parallelization is difficult due to dynamic features such as pointer operation and polymorphism in C/C++ language. This study focuses on verifying the conditions of parallelization rather than focusing on fully automatic parallelization, and providing advice to developers in detail if parallelization is not possible.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.622-625
• /
• 2008

While the research for flow over a circular cylinder has been actively carried out up to the present, it has been known that the flow has not been clarified even now. Various complex flow and aero-acoustic characteristics exist around a circular cylinder such as flow separation, wake and pressure wave propagation. In this paper, research was carried out for wake flow and aeroacoustics over a circular cylinders by using high order, high resolution techniques that are used in two dimensional aero- acoustic analysis. OpenMP parallel processing method was used. For the numerical result, the periodic characteristic of Strouhal Number due to vortex shedding was comparatively analyzed with other experiment values and two dimensional numerical results.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.55.1-55.1
• /
• 2020

In an attempt to investigate the nonlinear dynamics such as shock, shear, and turbulence associated with ultra-relativistic jets, we develop a new relativistic hydrodynamics (RHD) code based on the weighted essentially non-oscillatory (WENO) scheme. It is a 5th-order accurate, finite-difference scheme, which has been widely used for solving hyperbolic systems of conservation equations. The code is parallelized with MPI and OpenMP. Through an extensive set of tests, the accuracy and efficiency of different WENO reconstructions, and different time discretizations are assessed. Different implementations of the equation of state (EOS) for relativistic fluid are incorporated, As the fiducial setup for simulations of ultra-relativistic jets, we adopt the EOS in Ryu et al. (2006) to treat arbitrary adiabatic index of relativistic fluid, the WENO-Z reconstructions to minimize numerical dissipation without loss of stability, and the strong stability preserving Runge-Kutta (SSPRK) method to achieve stable time stepping with large CFL numbers. In addition, the code includes a high-order flux averaging along the transverse directions for multi-dimensional problems, and the modified eigenvalues for the acoustic modes to effectively control the carbuncle instability. We find that the new code performs satisfactorily simulations of ultra-relativistic jets.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.3
• /
• pp.171-178
• /
• 2020

In this study, we develop MPI-OpenMP hybrid parallelization for multibody peridynamic simulations. Peridynamics is suitable for analyzing complicated dynamic fractures and various discontinuities. However, compared with a conventional finite element method, nonlocal interactions in peridynamics cost more time and memory. In multibody peridynamic analysis, the costs increase due to the additional interactions that occur when computing the nonlocal contact and ghost interlayer models between adjacent bodies. The costs become excessive when further refinement and smaller time steps are required in cases of high-velocity impact fracturing or similar instances. Thus, high computational efficiency and performance can be achieved by parallelization and optimization of multibody peridynamic simulations. The analytical code is developed using an Intel Fortran MPI compiler and OpenMP in NURION of the KISTI HPC center and parallelized through MPI-OpenMP hybrid parallelization. Further parallelization is conducted by hybridizing with OpenMP threads in each MPI process. We also try to minimize communication operations by model-based decomposition of MPI processes. The numerical results for the impact fracturing of multiple bodies show that the computing performance improves significantly with MPI-OpenMP hybrid parallelization.

• Nuclear Engineering and Technology
• /
• v.51 no.5
• /
• pp.1218-1230
• /
• 2019

A sub-channel solver, named ${\underline{S}}teady$ and ${\underline{T}}ransient$ ${\underline{A}}nalyzer$ for ${\underline{R}}eactor$ ${\underline{T}}hermal$ hydraulics (START), has been developed using the homogenous model for two-phase conditions of light water reactors. The code is developed as a fast and accurate TH-solver for coupled and multi-physics calculations. START has been validated against the NUPEC PWR Sub-channel and Bundle Test (PSBT) database. Tests like single-channel quality and void-fraction for steady state, outlet fluid temperature for steady state, rod-bundle quality and void-fraction for both steady state and transient conditions have been analyzed and compared with experimental values. Results reveal a good accuracy of solution for both steady state and transient scenarios. Axially different values for turbulent mixing coefficient are used based on different grid-spacer types. This provides better results as compared to using a single value of turbulent mixing coefficient. Code-to-code evaluation of PSBT results by the START code compares well with other industrial codes. The START code has been parallelized with the OpenMP algorithm and its numerical performance is evaluated with a large whole PWR core. Scaling study of START shows a good parallel performance.