Platform for Assignment

First OpenMP program
------------------------

1. Download test-openmp.c, Makefile, sample-script
    - The script runs a simple OpenMP program on a single node using
2. Login to ssl cluster (replace "secsab" with your user-id)
    >> ssh secsab@10.16.38.145

   - Password: serc123
3. Create a directory called omp-test
    In another terminal, transfer the three downloaded files from your unix machine to the sslcluster's omp-test directory using scp:
    e.g., >> scp submit-script secsab@10.16.38.145:/home/secsab/omp-test
4. Compile using
>> make
5. In the submission script, change " /home/secsab/omp-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 96 MPI processes on 96 cores across 12 nodes with 8 processes per node.
2. Login to turing cluster with your created account.
    >> ssh <your username>@turing.cds.iisc.ac.in

   - Password: <your password>
3. Create a directory called mpi-test
    In another terminal, transfer the three downloaded files from your unix machine to the turing cluster's mpi-test directory using scp:
    e.g., >> scp submit-script <username>@turing.cds.iisc.ac.in:/home/<username>/mpi-test
4. Compile using
>> make
5. In the submission script, change " /home/vss/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 sslgpu cluster with your created account.
    >> ssh <your username>@10.16.38.146

   - Password: <your password>
3. Create a directory called cuda-test
    In another terminal, transfer the three downloaded files from your unix machine to the cluster's cuda-test directory using scp:
    e.g., >> scp submit-script <username>@10.16.38.146:/home/<username>/cuda-test
4. Compile using
>> make
5. In the submission script, change " /home/vss/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. In your output file, you should see "Correct!"


Happy CUDA!