info specific to bow, minnewanka, waterton

A CFI proposal by Profs. Stastna, Lamb, and Waite resulted in acquisition of new servers in 2017. Note that this page is incomplete and is being developed as these machines are deployed.

Hostnames (make/model)

• bow.math.private.uwaterloo.ca (SGI C2112-GP2)
• minnewanka.math.private.uwaterloo.ca (SGI C1104-GP2)
• waterton.math.private.uwaterloo.ca (SGI C1104-GP2)

System Administration

• MFCF administers these machines. Users do not have root access.
• Home directories are common with the previous machines via NFS
• System management is done by SaltStack software, unlike hood and thelon which are managed using MFCF's XHier
  • this means things will be different
  • applications are not under the /software directory anymore
  • default PATH does not have everything in it
    • use modules to load things that aren't in default locations like /usr/bin
      • to see a list of available modules, run

        module avail

      • load one using its exact name as shown in the list e.g. Matlab,

        module load matlab/2017a-research

Hardware

Each machine has:

• 2x Intel Xeon E5-2690v4 (Broadwell) CPUs, 2.6 GHz, 14 core
  • details on ark.intel.com
• 128 GB RAM
• 40 gigabit private network link for faster MPI
• 1 gigabit public network link (except bow has 10 gigabit)

Operating System Software and vendor add-ons

• CentOS 7.4
• SGI Foundation 2.16
• SGI Accelerate 1.14
• SGI Performance Suite 1.14 with an accelerated MPI called MPT 2.16

Application Software, Development Environment

Wherever satisfactory versions are provided by the OS distribution, things like library and include files are installed at default locations such as /usr/lib64 and /usr/include.

Compilers

• gcc 4.8.5 is in standard search rules, no need to load it with a module command
• Intel compilers etc. are not yet installed

MPI environments

Choose from MPICH, OpenMPI, and MPT

• MPICH 3.0

  • module load mpi/mpich-x86_64

• OpenMPI 1.10

  • module load mpi/openmpi-x86_64

• SGI/HPE MPT
  • This claims to be a tuned MPI that should perform best. You may wish to run some comparisons to see which MPI works best for you.
  • Includes an mpicc command.
  • Documentation at /opt/hpe/hpc/mpt/mpt-2.16/doc/README.relnotes

  • module load mpt/2.16

Matlab

• module load matlab/2017a-research

Python

• default python is 2.7.5. Default python3 is 3.4.5
• NumPY, SciPY, etc. are installed

Models

• MIT GCM
  • there is a config file called bow_mpt in the repository
  • need to load the mpt/2.16 module first
  • ensure you call genmake2 with the -mpi flag
  • GNU Fortran compiler seems pickier about some things than Intel compiler so you may see new complaints about previously-working code

• NCL NCARG version 6.4.0, without OPeNDAP
  • set environment variable NCARG_ROOT to /opt/ncl-6.4.0 and add $NCARG_ROOT/bin to your $PATH
  • optionally, make a .hluresfile in your home directory if you want to customize your NCL graphical environment

• SPINS
  • so far we have one system configuration file
    • bow.gcc.mpt.blas.sh
    • with symbolic link to that called bow.sh, since it's the only one we have so far
  • as the name suggests, it is set up to expect GCC, SGI/HPE MPT, and default BLAS and LAPACK
    • so you need to load the MPT module first
  • we expect to develop alternative configuration files for other compilers, MPI implementations, and numerical libraries for comparison to find an optimum set-up
  • a SPINS to NetCDF converter is available at /usr/local/spinstools/bin/spins2netcdf

Visualization

• ParaView 5.4.1
  • installed at /opt/paraview/

• VisIT 2.13.0
  • installed at /opt/visit/