USING FLUENT FOR HPC IT MANAGEMENT OF FME, 3 RD MARCH 2011.

Slides:



Advertisements
Similar presentations
CCPR Workshop Lexis Cluster Introduction October 19, 2007 David Ash.
Advertisements

Software Tools Using PBS. Software tools Portland compilers pgf77 pgf90 pghpf pgcc pgCC Portland debugger GNU compilers g77 gcc Intel ifort icc.
PBS Job Management and Taskfarming Joachim Wagner
Running Jobs on Jacquard An overview of interactive and batch computing, with comparsions to Seaborg David Turner NUG Meeting 3 Oct 2005.
IT MANAGEMENT OF FME, 21 ST JULY  THE HPC FACILITY  USING PUTTY AND WINSCP TO ACCESS THE SERVER  SENDING FILES TO THE SERVER  RUNNING JOBS 
Introduction to HPC Workshop October Introduction Rob Lane HPC Support Research Computing Services CUIT.
High Performance Computing
CSCI 1411 FUNDAMENTALS OF COMPUTING LAB Lab Introduction 1 Shane Transue MSCS.
Job Submission on WestGrid Feb on Access Grid.
Batch Process Overview. Batch Processes 2 What Do You Mean By Batch Processing? Allows for Mass Entry of Data All Processing of the Data Happens Without.
Sun Grid Engine Grid Computing Assignment – Fall 2005 James Ruff Senior Department of Mathematics and Computer Science Western Carolina University.
Quick Tutorial on MPICH for NIC-Cluster CS 387 Class Notes.
UNIX Chapter 00 A “ Quick Start ” into UNIX Operating System Mr. Mohammad Smirat.
CS1020: Intro Workshop. Topics CS1020Intro Workshop Login to UNIX operating system 2. …………………………………… 3. …………………………………… 4. …………………………………… 5. ……………………………………
Asynchronous Solution Appendix Eleven. Training Manual Asynchronous Solution August 26, 2005 Inventory # A11-2 Chapter Overview In this chapter,
High Performance Computing (HPC) at Center for Information Communication and Technology in UTM.
Understanding the Basics of Computational Informatics Summer School, Hungary, Szeged Methos L. Müller.
Introduction to UNIX/Linux Exercises Dan Stanzione.
ITCS 4/5145 Parallel Programming, UNC-Charlotte, B. Wilkinson, 2012, Jan 18, 2012assignprelim.1 Assignment Preliminaries ITCS 4145/5145 Spring 2012.
 Accessing the NCCS Systems  Setting your Initial System Environment  Moving Data onto the NCCS Systems  Storing Data on the NCCS Systems  Running.
ISG We build general capability Introduction to Olympus Shawn T. Brown, PhD ISG MISSION 2.0 Lead Director of Public Health Applications Pittsburgh Supercomputing.
BIOSTAT LINUX CLUSTER By Helen Wang October 11, 2012.
VIPBG LINUX CLUSTER By Helen Wang March 29th, 2013.
HPC at HCC Jun Wang Outline of Workshop1 Overview of HPC Computing Resources at HCC How to obtain an account at HCC How to login a Linux cluster at HCC.
Bigben Pittsburgh Supercomputing Center J. Ray Scott
Selecting, Formatting, and Printing a finished Report…….
CCPR Workshop Introduction to the Cluster July 13, 2006.
ACCESS IC LAB Graduate Institute of Electronics Engineering, NTU Usage of Workstation Lecturer: Yu-Hao( 陳郁豪 ) Date:
Network Queuing System (NQS). Controls batch queues Only on Cray SV1 Presently 8 queues available for general use and one queue for the Cray analyst.
Publishing Your Web Pages Ann Emmanuel SIUE Web Administrator
HPC for Statistics Grad Students. A Cluster Not just a bunch of computers Linked CPUs managed by queuing software – Cluster – Node – CPU.
Creating Programs on UNIX This term you can create programs on UNIX or you can create programs using a C++ compiler on your PC. This set of slides steps.
Software Tools Using PBS. Software tools Portland compilers pgf77 pgf90 pghpf pgcc pgCC Portland debugger GNU compilers g77 gcc Intel ifort icc.
Running Parallel Jobs Cray XE6 Workshop February 7, 2011 David Turner NERSC User Services Group.
ISG We build general capability Introduction to Olympus Shawn T. Brown, PhD ISG MISSION 2.0 Lead Director of Public Health Applications Pittsburgh Supercomputing.
Introduction to HPC Workshop October Introduction Rob Lane & The HPC Support Team Research Computing Services CUIT.
Unix Servers Used in This Class  Two Unix servers set up in CS department will be used for some programming projects  Machine name: eustis.eecs.ucf.edu.
FTP COMMANDS OBJECTIVES. General overview. Introduction to FTP server. Types of FTP users. FTP commands examples. FTP commands in action (example of use).
Portable Batch System – Definition and 3 Primary Roles Definition: PBS is a distributed workload management system. It handles the management and monitoring.
Advanced topics Cluster Training Center for Simulation and Modeling September 4, 2015.
Wouter Verkerke, NIKHEF 1 Using ‘stoomboot’ for NIKHEF-ATLAS batch computing What is ‘stoomboot’ – Hardware –16 machines, each 2x quad-core Pentium = 128.
Active-HDL Server Farm Course 11. All materials updated on: September 30, 2004 Outline 1.Introduction 2.Advantages 3.Requirements 4.Installation 5.Architecture.
Introduction to HPC Workshop March 1 st, Introduction George Garrett & The HPC Support Team Research Computing Services CUIT.
NREL is a national laboratory of the U.S. Department of Energy, Office of Energy Efficiency and Renewable Energy, operated by the Alliance for Sustainable.
PuTTY Introduction to Web Programming Kirkwood Continuing Education by Fred McClurg © Copyright 2016, All Rights Reserved ssh client.
Assignprelim.1 Assignment Preliminaries © 2012 B. Wilkinson/Clayton Ferner. Modification date: Jan 16a, 2014.
Using ROSSMANN to Run GOSET Studies Omar Laldin ( using materials from Jonathan Crider, Harish Suryanarayana ) Feb. 3, 2014.
An Brief Introduction Charlie Taylor Associate Director, Research Computing UF Research Computing.
Editing, Transferring, and Running Files on Vieques Daniel Malmer Dowell Lab Short Reads Course 6/9/15.
Advanced Computing Facility Introduction
GRID COMPUTING.
Auburn University
Welcome to Indiana University Clusters
PARADOX Cluster job management
CS1010: Intro Workshop.
Unix Scripts and PBS on BioU
HPC usage and software packages
Welcome to Indiana University Clusters
How to use the HPCC to do stuff
BIOSTAT LINUX CLUSTER By Helen Wang October 29, 2015.
CommLab PC Cluster (Ubuntu OS version)
Assignment Preliminaries
Practice #0: Introduction
Postdoctoral researcher Department of Environmental Sciences, LSU
Introduction to HPC Workshop
Compiling and Job Submission
CCR Advanced Seminar: Running CPLEX Computations on the ISE Cluster
Quick Tutorial on MPICH for NIC-Cluster
Working in The IITJ HPC System
Maxwell Compute Cluster
Presentation transcript:

USING FLUENT FOR HPC IT MANAGEMENT OF FME, 3 RD MARCH 2011

important notes This is not a FLUENT introductory course but an advance course of existing Fluent users to run their models on HPC.

Table of contents THE HPC FACILITY USING PUTTY AND WINSCP TO ACCESS THE SERVER SENDING FILES TO THE SERVER RUNNING JOBS MONITORING JOBS COPY RESULTS BACK FROM THE SERVER Using CYGWIN to ACCESS Fluent

cict Sunfire 8 CPUs x 6 Nodes - Quad-Core AMD Opteron(tm) Processor 2376 HE (2.3 GHz) Interconnected using Infiniband and Ethernet Each Node has 8 GB of memory Storage capacity GB at the moment

QUEUE SYSTEM Using Torque - torque-server cri.slc4 and torque-mom cri.slc4 Scheduler - maui-server-3.2.6p21- snap slc4 Current MPI does not utilise Infiniband. This soon will be fixed.

Table of contents THE HPC FACILITY USING PUTTY AND WINSCP TO ACCESS THE SERVER SENDING FILES TO THE SERVER RUNNING JOBS MONITORING JOBS COPY RESULTS BACK FROM THE SERVER

installing Cygwin Cygwin is an opensource software that can be installed on your personal Windows XP or 7 computer. It can be downloaded from To use its X-server functionality, please visit The userguide is at ug.html ug.html

running Cygwin After installation, a program called Cygwin will be installed. A program called Cygwin/X can be executed. The X-server will be running. Leave it there.

accessing the system Using putty.exe – Using winscp.exe –

Login into the system via putty and winsCP Server : fkm.utm.my Port : 2323 or Server : ce.utmgrid.utm.my Port : 22

Via putty

via putty, enable tunnelling Enable X tunnelling if you want to use CYGWIN X-server to run Fluent GUI from the HPC server.

via putty press YES

via putty

via winscp Click NEW

via winscp

1.click YES 2.click Continue 3.enter Your Password

VIA winSCP

SENDING FILES TO THE SERVER 1.Search files to be transferred at the left panel. 2.Create a new directory on the right panel. 3.Select files on the left panel. 4.Copy from left to right.

FLUENT On HPC, you can run Fluent in the Fluent windowing environment or submit your application which needs more than 30 minutes of CPU time to run to the PBS queue. Interactive sessions are recommended only for pre- and postprocessing and for the solution of small problems. Larger problems should be run as batch jobs for either serial runs or parallel runs of Fluent. The user may check the possible command line options by entering the command.

FLUENT Fluent interface can be access via CYGWIN. Cygwin is an opensource software that could emulate X-server. The X-server is used to run ANSYS Workbench. Run the following command in your putty. /opt/exp_soft/share/istas/ansys_inc/v121/Framework/bin/Linux64/runwb2

FLUENT : Example Workbench

Fluent Type ‘pico model_journal’ Enter file/read-case your_input_file.cas solve/init/initialize-flow solve/iterate 400 file/binary-files n file/confirm-overwrite n file/write-data your_output_file.dat exit y  Press Control–O to save  Press Enter  Press Control-X to exit

fluent prepare the pbs-script, type ‘pico pbs-script’ Enter the following #!/bin/sh #PBS -q utm #PBS -N istas.model3d #PBS -l nodes=1:ppn=8 #PBS -M #PBS -m abe nCPU=8 version=3d journal=model_journal cd $PBS_O_WORKDIR /opt/exp_soft/share/istas/ansys_inc/v121/fluent/bin/fluent $version -t$nCPU -g -i $journal - mpi=openmpi -cnf=$PBS_NODEFILE -ssh  Press Ctrl-O to save  Press Enter  Press Ctrl-X to exit

fluent Finally we want to submit the job, just type ‘qsub pbs-script’ type ‘qstat’ to see the status of your job. an will be sent to you to let you know the job has started. another will be sent to let you know the job has ended. You could open WINSCP again to copy the output back to your PC.

USEFUL PBS commands qsub: Once a PBS job script is created, it is submitted to PBS via the qsub command. In its simplest form, qsub takes a single parameter, the name of the script file that you wish to submit. qstat: The qstat command will allow you to view the contents of the PBS queue. node1:~/test> qstat Job id Name User Time Use S Queue node1 testjob psmith 0 R default

cont... qdel: The qdel command takes a single argument, a job number. You can use qdel to abort execution of your job: qdel 147 would cancel execution of the job shown in the qstat example above. qalter: The qalter command is helpful for altering the parameters of a job after it's submitted. qalter takes two arguments: the PBS directive that you wish to change (like -l), and the job number that you want to change. For example, if you forgot to set the walltime that your job requires, you can change it after it's been submitted: node1:~> qalter -l walltime=4:00:00 147

cont... pbsnodes: The pbsnodes command, while a useful PBS administration command, can also be informative to the PBS user. pbsnodes -a will list all PBS nodes, their attributes, and job status. This is a useful way to get a list of valid machine properties for use in a #PBS -l directive. node1:~> pbsnodes -a node2 state = free np = 2 properties = gigabit,pcn,m2048,dual,p1800,athlon ntype = cluster

Exercise Download this file and unzip it in a folder. There are four files in the zip file, Makefile, model.cas, model_journal, pbs-script

Exercise Open WinSCP Click New Enter Hostname : ce.utmgrid.utm.my Enter your username Enter your password Transfer the content of Fluent folder to the server.

Exercise Copy the whole directory from left to right.

Exercise Open Putty Enter hostname : ce.utmgrid.utm.my Click Open Enter your username Enter your password If all are OK, you will be getting a Unix shell. ~/ $ _

Exercise Login to the server via putty.

Exercise Common Unix Commands CommandDescription ls -llist directory mkdir xxxcreate directory xxx rm xxxdelete file xxx cd..back to previous level directory cd -shifted to previous directory exitlog off from server pwdcurrent director whowho is currently logging cp aaa bbbcopy file aaa to a new file bbb mv aaa bbbmove/rename file aaa to file bbb clearclear screen

Exercise Type ‘ls’ to list the content of the directory. You will see the name of the directory that contains the Fluent file that was uploaded a moment ago. Type ‘cd ’. Move the directory. Type ‘ls’ again.

Exercise Now we can to see the content of our model_journal file. Type ‘pico model_journal’. You will see a series of Fluent command to be executed when your model is ran. Type ‘control-x’ to exit.

Exercise To edit the content of pbs-script, type ‘pico pbs- script’ You could edit the content of PBS-SCRIPT and to exit without save – type ‘control-x’ and type ‘n’ for no to save. To save the content, type ‘control-x’ and type ‘y’ for yes to save. Now you are satisfied with your setting.

Exercise #!/bin/sh #PBS -q utm #PBS -N istas.model3d.16nodes #PBS -l nodes=1:ppn=4 #PBS -M #PBS -m abe nCPU=4 version=3d journal=model_journal cd $PBS_O_WORKDIR # in one line... /opt/exp_soft/share/istas/ansys_inc/v121/fluent/bin/fluent $version -t$nCPU -g -i $journal -cnf=$PBS_NODEFILE -ssh Queue name : utm Job name node x ppn = no cpu required address when start, error and finish fluent version used the name of the journal file

Exercise File “model_journal” file/read-case model.cas solve/init/initialize-flow solve/iterate 400 file/binary-files n file/confirm-overwrite n file/write-data model.dat exit y input output This file automates the running of Fluent commands during the execution. The content of this file depends on the type of problem you are solving.

Exercise Now it is time to run the job, all you need to do is to run the following command, qsub pbs-script If nothing is wrong, your job will be placed in a queue and if there is available CPUs your job will be executed immediately.

Exercise You could monitor the progress of your job by type command ‘qstat’. If the list is too long, type ‘qstat | less’. Type ‘q’ to exit. Example of qstat is

ce.utmgrid.utm.my: Req'd Req'd Elap Job ID Username Queue Jobname SessID NDS TSK Memory Time S Time ce.utmgri pgjsaeed utm pgjsaeed.model3d : R 392: ce.utmgri aliff utm Drop : R 604: ce.utmgri smahmad3 utm FJSSPHM111.sh : R 136: ce.utmgri smahmad3 utm FJSSPHM225.sh : R 65: ce.utmgri smahmad3 utm FJSSPHM226.sh : R 57: ce.utmgri smahmad3 utm FJSSPHM231.sh : R 57: ce.utmgri smahmad3 utm FJSSPHM232.sh : Q ce.utmgri smahmad3 utm FJSSPHM233.sh : Q ce.utmgri smahmad3 utm FJSSPHM234.sh : Q -- Username Exercise Job numberJob name Max time allowed Q – still waiting R - running Elapse Time

Exercise Tips and tricks 1.Use a small number of CPUs to get your job executes earlier in the queue. 2.Start from small problem. 3.Always delete old unused files. Keep the storage space free.

Thank you