| 1 | == drbl-mpi shell script == |
| 2 | |
| 3 | Abstract [[br]] |
| 4 | I.Introduction [[br]] |
| 5 | II.LAMMPS simulation [[br]] |
| 6 | III.DRBL AND ONEMPI archtiecture [[br]] |
| 7 | IV.LAMMPS Benchmark [[br]] |
| 8 | V.Conclusions [[br]] |
| 9 | |
| 10 | Abstract― [[br]] |
| 11 | The LAMMPS is classical molecular dynamics software which supports also large scale atomic massively parallel simulation. [[br]] |
| 12 | The code has been run on a PC cluster with using DRBL (Diskless Remote Boot in Linux)-ONEMPI. MPICH2 provide an MPI [[br]] |
| 13 | implementation that supports different computing and communication platform. How-ever, MPICH2 has still many installation [[br]] |
| 14 | steps that are complicate. Therefore, the paper provides DRBL-ONEMPI free software to deploy desktop clusters. It can [[br]] |
| 15 | construct quickly a multicores architecture environment and a convenient management for your environment. The DRBL-ONEMPI [[br]] |
| 16 | gives user some useful installation process and assists system administrators to deploy their own private cluster environment. [[br]] |
| 17 | We build a PC cluster environment, and runs in parallel using MPICH2 on our PC cluster with diskless nodes. We will introduce [[br]] |
| 18 | the basic architecture of DRBL-ONEMPI and present some design. [[br]] |
| 19 | |
| 20 | Keywords―LAMMPS, molecular dynamics, MPICH2, DRBL-ONEMPI. [[br]] |
| 21 | |
| 22 | I.Introduction [[br]] |
| 23 | |
| 24 | LAMMPS is created by Sandia National La-boratories, a US Department of Energy laboratory. LAMMPS is classical molecular dynamics [[br]] |
| 25 | simulation software, integrates Newton`s equation of motion, is an open source code, and runs on single processors or parallel [[br]] |
| 26 | programming with using message-passing interface. The LAMMPS source is widely applied in the semiconductors, biomolecular, polymers, [[br]] |
| 27 | coarse-grained and microscopic, etc. It has been used to simulate in the chemistry and semiconductor research. The LAMMPS has lots [[br]] |
| 28 | of library to use, modify, or extended LAMMPS in your choose. [[br]] |
| 29 | In past few years, PC cluster are more and more popular in high performance computing be-cause of computing ability. However, [[br]] |
| 30 | it is difficult for the administrator manage lots of computers, to deploy the system environmental and to configure the installation [[br]] |
| 31 | of the cluster. The DRBL-ONEMPI provides a way to manage the pc cluster environ-ment, such as the installation of the cluster, the [[br]] |
| 32 | deployment system environment, the user man-agement, the system monitor and easy to use it. [[br]] |
| 33 | The DRBL-ONEMPI has two components package, including DRBL and ONEMPI. The DRBL is a diskless or systemless environment for client [[br]] |
| 34 | machines and an open source solution to managing the deployment of the GNU/Linux oper-ating system across many clients. Hence, we [[br]] |
| 35 | have an ideal plan for running MPI programming on the diskless environment and so to exploit ONEMPI. The ONEMPI make user avoid complicated [[br]] |
| 36 | the MPICH2 installation process. However, we combine DRBL with ONEMPI which rename DRBL-ONEMPI. In general, the pc cluster is difficult [[br]] |
| 37 | to manage and deploy environment. However, we use DRBL-ONEMPI to manage and execute mpich2 on our computing environment. The user just [[br]] |
| 38 | enters some instructions on command-line that accomplish diskless environment. [[br]] |
| 39 | In section.2, we will introduce LAMMPS simulation software. In section.3, the DRBL and ONEMPI system are presented in detail. In sec-tion.4, [[br]] |
| 40 | the simulation and benchmark results are discussed. [[br]] |
| 41 | |
| 42 | |
| 43 | II. LAMMPS Simulation [[br]] |
| 44 | The LAMMPS has been used wildly in ma-terial processing, such as etching, deposition, sput-tering and surface cleaning, etc. some people also use [[br]] |
| 45 | LAMMPS to apply mechanical engineering, such as computational fluid dynamics (CFD), Fracture Mechanics, Micro and Nano Mechanics, etc. The LAMMPS [[br]] |
| 46 | is popular one of molecular dynamics software and lots of library. [[br]] |
| 47 | The LAMMPS applied process as follows: [[br]] |
| 48 | (1) To input a script file for LAMMPS the initial configuration. [[br]] |
| 49 | (2) To create a particle and model types, such as atoms, coarse-grained particles, all-atom poly-mers, organic molecules, proteins, DNA, etc. [[br]] |
| 50 | (3) To choose force fields, the potential has Len-nard-Jones, Morse, Tersoff and EAM, etc. [[br]] |
| 51 | (4) To construct boundary and constraints conditions. [[br]] |
| 52 | (5) To choose integrators, such as velocity-Verlet integrator, Brownian dynamics, rigid body in-tegration, etc. [[br]] |
| 53 | (6) To run program and Output file. [[br]] |
| 54 | |
| 55 | III. DRBL and ONEMPI design architecture [[br]] |
| 56 | A. DRBL Architecture [[br]] |
| 57 | Diskless Remote Boot in Linux (DRBL) is an open source solution to managing the deploy-ment of the GNU/Linux operating system across many clients. [[br]] |
| 58 | DRBL supports lots of popular GNU/Linux distributions, and it is developed based on diskless and systemless environment for client machines. Figure 1 [[br]] |
| 59 | shows DRBL system architec-ture. DRBL uses PXE/Etherboot, DHCP, TFTP, NFS and NIS to provide services to client machines, so it is not necessary to [[br]] |
| 60 | install GNU/Linux on the client hard drives individually. Users just prepare a server machine for DRBL to be installed as a DRBL server, and follow [[br]] |
| 61 | the DRBL installation wizard to configure and dispose the environment for client machines step by step. It’s really an easy job to deploy a DRBL [[br]] |
| 62 | environment on clustering systems even for a GNU/Linux beginner, hence cross-platform and user-friendly are the key factors that make the DRBL become [[br]] |
| 63 | a superior clustering tool. DRBL can efficiently deploy diskless or dis-kfull cluster environment, and manage client. It configures these services [[br]] |
| 64 | (TFTP, NIS, DHCP, and NFS) to build a cluster environment. According to this implementation, administrator just needs two steps to deploy cluster [[br]] |
| 65 | environment. (1) Step 1: In-stalls DRBL packages and generates kernel and in-itrd for client; (2) Step 2: setup environment para-meters, such IP address, [[br]] |
| 66 | and numbers of clients. It also provides cluster management and cluster system transformation (diskfull or diskless system). The Figure 1 shows DRBL [[br]] |
| 67 | system architecture [[br]] |
| 68 | |
| 69 | |
| 70 | |