High Performance Computing Systems for IU Researchers – An Introduction IUB Wells Library 10-Sep-2012 Jenett Tillotson George Turner

Slides:



Advertisements
Similar presentations
Illinois Campus Cluster Program User Forum April 24, 2012 NCSA Room :00 AM - 11:00 AM.
Advertisements

Using the Argo Cluster Paul Sexton CS 566 February 6, 2006.
Job Submission Using PBSPro and Globus Job Commands.
Network for Computational Nanotechnology (NCN) Purdue, Norfolk State, Northwestern, UC Berkeley, Univ. of Illinois, UTEP Basic Portable Batch System (PBS)
Southgreen HPC system Concepts Cluster : compute farm i.e. a collection of compute servers that can be shared and accessed through a single “portal”
Software Tools Using PBS. Software tools Portland compilers pgf77 pgf90 pghpf pgcc pgCC Portland debugger GNU compilers g77 gcc Intel ifort icc.
An overview of Torque/Moab queuing. Topics ARC topology Authentication Architecture of the queuing system Workflow Job Scripts Some queuing strategies.
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.
ISG We build general capability Job Submission on the Olympus Cluster J. DePasse; S. Brown, PhD; T. Maiden Pittsburgh Supercomputing Center Public Health.
High Performance Computing
Job Submission on WestGrid Feb on Access Grid.
Using the BYU Supercomputers. Resources Basic Usage After your account is activated: – ssh ssh.fsl.byu.edu You will be logged in to an interactive node.
Quick Tutorial on MPICH for NIC-Cluster CS 387 Class Notes.
J. Skovira 5/05 v11 Introduction to IBM LoadLeveler Batch Scheduling System.
ISG We build general capability Purpose After this tutorial, you should: Be comfortable submitting work to the batch queuing system of olympus and be familiar.
Introduction to UNIX/Linux Exercises Dan Stanzione.
Research Computing with Newton Gerald Ragghianti Newton HPC workshop Sept. 3, 2010.
Electronic Visualization Laboratory, University of Illinois at Chicago MPI on Argo-new Venkatram Vishwanath Electronic Visualization.
ISG We build general capability Introduction to Olympus Shawn T. Brown, PhD ISG MISSION 2.0 Lead Director of Public Health Applications Pittsburgh Supercomputing.
MSc. Miriel Martín Mesa, DIC, UCLV. The idea Installing a High Performance Cluster in the UCLV, using professional servers with open source operating.
VIPBG LINUX CLUSTER By Helen Wang March 29th, 2013.
Bigben Pittsburgh Supercomputing Center J. Ray Scott
March 3rd, 2006 Chen Peng, Lilly System Biology1 Cluster and SGE.
17-April-2007 High Performance Computing Basics April 17, 2007 Dr. David J. Haglin.
How to get started on cees Mandy SEP Style. Resources Cees-clusters SEP-reserved disk20TB SEP reserved node35 (currently 25) Default max node149 (8 cores.
Introduction to Using SLURM on Discover Chongxun (Doris) Pan September 24, 2013.
Batch Systems In a number of scientific computing environments, multiple users must share a compute resource: –research clusters –supercomputing centers.
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.
Using the BYU SP-2. Our System Interactive nodes (2) –used for login, compilation & testing –marylou10.et.byu.edu I/O and scheduling nodes (7) –used for.
HPC for Statistics Grad Students. A Cluster Not just a bunch of computers Linked CPUs managed by queuing software – Cluster – Node – CPU.
Using hpc Instructor : Seung Hun An, DCS Lab, School of EECSE, Seoul National University.
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.
1 HPCI Presentation Kulathep Charoenpornwattana. March 12, Outline Parallel programming with MPI Running MPI applications on Azul & Itanium 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.
Introduction to HPC Workshop October Introduction Rob Lane & The HPC Support Team Research Computing Services CUIT.
Portable Batch System – Definition and 3 Primary Roles Definition: PBS is a distributed workload management system. It handles the management and monitoring.
Wouter Verkerke, NIKHEF 1 Using ‘stoomboot’ for NIKHEF-ATLAS batch computing What is ‘stoomboot’ – Hardware –16 machines, each 2x quad-core Pentium = 128.
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.
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.
Information Technology Services Brett D. Estrade, LSU – High Performance Computing Phone:
Advanced Computing Facility Introduction
Hackinars in Bioinformatics
GRID COMPUTING.
Specialized Computing Cluster An Introduction
Welcome to Indiana University Clusters
PARADOX Cluster job management
First proposal for a modification of the GIS schema
Unix Scripts and PBS on BioU
HPC usage and software packages
Welcome to Indiana University Clusters
How to use the HPCC to do stuff
Joker: Getting the most out of the slurm scheduler
Hodor HPC Cluster LON MNG HPN Head Node Comp Node Comp Node Comp Node
CommLab PC Cluster (Ubuntu OS version)
Practice #0: Introduction
Welcome to our Nuclear Physics Computing System
Paul Sexton CS 566 February 6, 2006
Introduction to HPC Workshop
Center for High Performance Computing
Compiling and Job Submission
CCR Advanced Seminar: Running CPLEX Computations on the ISE Cluster
High Performance Computing in Bioinformatics
Queueing System Peter Wad Sackett.
Introduction to High Performance Computing Using Sapelo2 at GACRC
Quick Tutorial on MPICH for NIC-Cluster
Presentation transcript:

High Performance Computing Systems for IU Researchers – An Introduction IUB Wells Library 10-Sep-2012 Jenett Tillotson George Turner High Performance – Systems

Getting Started BigRed: Quarry:

Getting an account Manage my IU computing accounts create more accounts choose "BigRed" or "Quarry” Takes about 15 minutes You will receive a welcome

Logging in ssh bigred.teragrid.iu.edu ssh quarry.teragrid.iu.edu MOTD

Nodes BigRed: b1-b1050, s1c1b1-s19c3b14 Quarry-classic: b001-b140, q001-q140 Quarry-pg: p1-p230, pg1-pg230

Head nodes BigRed: b513 - b516 Quarry-classic: b001 - b004 Quarry-pg; p230

Wild West nodes BigRed: b509-b512 Quarry: q005-q008

Compute nodes BigRed: b1-b508, b561-b1050 Quarry: q009-q140, pg1-pg229

File systems Home directory DataCapacitor (Lustre)

File systems : Home directory /N/u/{username}/BigRed /N/u/{username}/Quarry ${HOME} 10GB quota quota -v Slow, limited, backed up

File systems : DataCapacitor (lustre) IU users: /N/dc/scratch/{username} Fast, unlimited, not backed up Permanent project file space available

Softenv Modifies environment ${PATH} and ${MANPATH} softlist soft add.soft resoft

Resource Manager Keeps tracks of resources: nodes, jobs, queues BigRed – LoadLeveler llsubmit llq llcancel llclass Quarry – TORQUE qsub qstat –a –u $USER qdel qstat -Q

Queues : BigRed LONG: 32 nodes/job, 64 nodes/user, 14 days wall clock time NORMAL: 256 nodes/job, 512 nodes/user, 2 days wall clock time SERIAL: 1 proc/job, 512 proc/user, 2 days wall clock time DEBUG: 4 nodes/jobs, 4 nodes/user, 15 minutes wall clock time, 1 idle job Limit of 768 jobs in all the queues per user Limit of 16 idle jobs per user (except for the DEBUG queue)

Queues : Quarry long: 42 nodes/job, 14 days wall clock time, 50 jobs/user normal: 6 nodes/job, 7 days wall clock time, 500 jobs/user serial: 1 node/job, 12 hours wall clock time, 500 jobs/user debug: 4 nodes/job, 15 minutes wall clock time,2 jobs/user himem: 28 nodes/job, 14 days wall clock time, 50 jobs/user batch: default queue Limit of 16 idle jobs per user

Job Scripts

BigRed #!/bin/bash -l step_name = step1 initialdir = /N/u/jtillots/BigRed/myoutput output = step1.out error = step1.err notification = always notify_user = class = DEBUG wall_clock_limit = 15:00 account_no = NONE queue /bin/date sleep 10 /bin/date

Quarry #!/bin/bash -l #PBS -N step1 #PBS -j oe #PBS -k o #PBS -m abe #PBS -M #PBS -q debug #PBS -l nodes=1,walltime=15:00 /bin/date sleep 10 /bin/date

Job ids BigRed: s10c2b5.{jobid}.0 Quarry: {jobid}.qm2

Scheduler : Moab Decides which jobs get run on what nodes at what time. showq by queue:-w class={queuename} running jobs:-r idle jobs:-i blocked jobs:-b checknode checkjob showstart Single-user mode

Job Priority mdiag -p Fair share XFactor QOS Backfill showbf