Documentation
Rate This Document
Findability
Accuracy
Completeness
Readability
SubmitClose

Running and Verification

Single Node

  1. Use PuTTY to log in to the server as the root user.
  2. Decompress the TEST41 test case package.
    tar -zxf TEST41.tar.gz
  3. Go to the TEST41 test case directory.
    cd TEST41/NHC
  4. Run the test case on the single node.
    mpirun --allow-run-as-root -np 8 -mca btl ^openib DLPOLY.X

    The -np parameter indicates the total number of processes, and the -N parameter indicates the number of processes used by each node. Set the parameters based on the actual node configuration.

    time elapsed since job start = XX seconds in the OUTPUT file indicates the performance. A smaller value of XX indicates higher performance.

    The following is an example of the output result.

Multiple Nodes

If multiple nodes are running, configure the network environment:

  • In the /etc/hosts file, add the IP addresses and host names of the nodes.
  • Enable SSH password-free login between the nodes.
  • Disable the firewall and ensure that clients and servers are not disconnected.
  1. Use PuTTY to log in to the server as the root user.
  2. Decompress the TEST41 test case package.
    tar -zxf TEST41.tar.gz
  3. Go to the TEST41 test case directory.
    cd TEST41/NHC
  4. Run the following command to create the hostfile file and add node information:
    echo -e 'node1\nnode2\n…\nnodex' > /path/to/HOSTFILE

    In the preceding command, node1, node2, ..., and nodex indicate the host names of the nodes. You can run the hostname command to query the host names. \n indicates a newline character.

  5. In the window of node2, set the environment variables.
    vi /root/.bashrc
export PATH=/opt/compiler/bisheng-compiler-1.3.1-aarch64-linux/bin:$PATH
export LD_LIBRARY_PATH=/opt/compiler/bisheng-compiler-1.3.1-aarch64-linux/lib:$LD_LIBRARY_PATH
export PATH=/path/to/DL_POLY/dl_poly-RELEASE-1-10/execute:$PATH
export INCLUDE=/path/to/hypermpi/hmpi/include
export PATH=/path/to/hypermpi/hmpi/bin:/path/to/hypermpi/ucx/bin:$PATH
export OPAL_PREFIX=/path/to/hypermpi/hmpi/
export LD_LIBRARY_PATH=/path/to/hypermpi/hmpi/lib:/path/to/hypermpi/ucx/lib:$LD_LIBRARY_PATH
  6. Run the test case on the multiple nodes.
    mpirun --allow-run-as-root -np 16 -N 8 -x PATH=$PATH -x LD_LIBRARY_PATH=$LD_LIBRARY_PATH -x OMP_NUM_THREADS=1 --hostfile /path/to/HOSTFILE -mca btl ^openib DLPOLY.X

    The -np parameter indicates the total number of processes, and the -N parameter indicates the number of processes used by each node. Set the parameters based on the actual node configuration. Alternatively, you do not need to specify the two parameters and the maximum number of processes will be used. The -x OMP_NUM_THREADS parameter indicates the number of threads to be used.