CDS Turing Cluster

The CDS Turing cluster has 24 nodes with 8 cores each.

First OpenMP program

  1. Download test-openmp.c, Makefile, sample-script. The script runs a simple OpenMP program on a single node.
  2. Login to the turing cluster with your account.
  3. Create a directory called openmp_test. In another terminal, transfer the three downloaded files from your unix machine to the turing cluster’s openmp_test directory using scp:
    >> scp submit-script <your-account>@<turing-cluster-ip>:<your-home-area>/openmp_test
  4. Compile using
    >> make
  5. In the submission script, change  “/home/<HOME>/openmp_test” to your directory containing test-openmp.c
  6. Submit to PBS using
    >> qsub sample-script
  7. Monitor your submitted job using
    >> qstat
  8. After your program finishes, you will see output of your program in “myjob<id>.o<num>” file. If your run produced error, you will see the error message in “myjob<id>.e<num>” file

Happy OpenMP!

 

First MPI program

  1. Download test-mpi.c, Makefile, sample-script. The script runs 32 MPI processes on 32 cores across 4 nodes with 8 processes per node..
  2. Login to the turing cluster with your account.
  3. Create a directory called mpi_test. In another terminal, transfer the three downloaded files from your unix machine to the turing cluster’s openmp_test directory using scp:
    >> scp submit-script <your-account>@<turing-cluster-ip>:<your-home-area>/mpi_test
  4. Compile using
    >> make
  5. In the submission script, change “/home/<HOME>/mpi_test” to your directory containing test-mpi.c
  6. Submit to PBS using
    >> qsub sample-script
  7. Monitor your submitted job using
    >> qstat
  8. After your program finishes, you will see output of your program in “myjob<id>.o<num>” file. If your run produced error, you will see the error message in “myjob<id>.e<num>” file

Happy MPI!

First CUDA program

  1. Download test-cuda.cu, Makefile, sample-script
  2. Login to the turing cluster with your account
  3. Create a directory called cuda_test. In another terminal, transfer the three downloaded files from your unix machine to the turing cluster’s cuda_test directory using scp:
    >> sc p submit-script <your-account>@<turing-cluster-ip>:<your-home-area>/cuda_test
  4. Compile using
    >> make
  5. In the submission script, change “ /home/secvss/cuda-test” to your directory containing test-cuda.cu
  6. Submit to PBS using
    >> qsub sample-script
  7. Monitor your submitted job using
    >> qstat
  8. After your program finishes, you will see output of your program in “myjob<id>.o<num>” file. If your run produced error, you will see the error message in “myjob<id>.e<num>” file.

Happy CUDA!