All Products
Search
Document Center

Elastic High Performance Computing:Submit a job

Last Updated:Jun 20, 2026

A job, which can be a shell script or an executable file, is the basic unit of work for high-performance computing (HPC) in an E-HPC cluster. This topic describes how to submit a job using the E-HPC client.

Prerequisites

Before you submit a job, you must prepare the job files and upload them to your E-HPC cluster.

The E-HPC client supports the following methods to upload job files:

  • Use the Data Management feature to create and edit job files, or upload local job files to the cluster. For more information, see Manage files.

  • Use the Session Management feature to remotely log on to the cluster and run commands to create job files. For more information, see Manage sessions.

Method 1: Submit a job from the client UI

  1. Log on to the E-HPC client.

    For more information, see Log on to the client.

  2. In the left-side navigation pane, choose Job Submission.

  3. Click Submit Job.

  4. In the panel that appears, configure the job parameters, and then click Submit Job.

    Parameter

    Description

    Queue

    The queue where the job runs. If a compute node is added to a specific queue, you must submit the job to that queue. Otherwise, the job fails. If no compute node is added to a queue, the job is sent to the scheduler's default queue.

    Job name

    The name of the job.

    If you need to automatically download and decompress job files, a directory with the same name as the job is created for the decompressed files.

    Command

    The command that the scheduler uses to run the job. This can be a script file, such as the job.pbs file in the /home/test directory, or a command string. Two scenarios are possible:

    • If the script file is executable, you can enter a relative path, such as ./job.pbs.

    • If the script file lacks execute permissions, you must enter the full command, such as /opt/mpi/bin/mpirun /home/test/job.pbs. If you use the PBS scheduler, you must add -- before the command, such as --/opt/mpi/bin/mpirun /home/test/job.pbs.

    Priority

    The priority of the job. Valid values: 0 to 9. A larger value indicates a higher priority. If the scheduling policy of the cluster is based on priority, jobs with higher priority are scheduled first.

    Number of compute nodes

    The number of compute nodes used to run the job.

    Number of tasks

    The number of tasks, or processes, that run on each compute node for this job.

    Maximum memory

    The maximum memory that can be used by each compute node for this job. By default, this parameter is empty, which indicates that memory usage is not limited.

    Runtime

    The maximum runtime for the job. If the job times out, it fails. By default, this parameter is empty, which indicates that the runtime is not limited.

    Number of threads

    The number of threads used by each task. If this parameter is left empty, the default value is 1.

    Number of GPUs

    The number of GPUs used by each compute node for this job. When you configure this parameter, make sure that the compute nodes are GPU-accelerated instances.

    Standard output path and standard error path

    The redirection paths, including filenames, for standard output (stdout) and standard error (stderr) in Linux.

    • stdout: The path to the standard output file.

    • stderr: The path to the standard error file.

    The cluster user must have write permissions on the specified paths. By default, output files are generated according to the scheduler settings.

    Add environment variables

    Add environment variables as needed.

Method 2: Submit a job from the CLI

  1. Remotely log on to the cluster.

    1. In the left-side navigation pane, choose Session Management.

    2. On the right page, click terminal.

  2. In the window that appears, run the command appropriate for your scheduler type to submit the job.

    For example, if you use the PBS scheduler and the job file is test.pbs, run the qsub test.pbs command to submit the job.

    For more information, see Submit a job from the command line.

Method 3: Submit a job using a job template

  1. Create a job template.

    1. On the Job Submission page, click Submit Job.

    2. In the Create Job panel, configure the job parameters.

      For parameter descriptions, see the Job parameter reference.

    3. Click Save as Template.

    4. In the dialog box that appears, enter a name for the template and click OK.

  2. On the Job Submission page, in the Job Submission Template section, find the desired job template and click the 提交作业图标 icon.

    Note

    Job templates appear as cards in this section. You can click the icons at the bottom of a card to submit a job, or to edit or delete the template.

  3. In the panel that appears, confirm the job parameters and click Submit Job.

Method 4: Submit a job using App Center

The E-HPC client provides a visual interface to configure software applications, such as GROMACS and Fluent. This lets you easily configure application-specific job parameters and quickly submit jobs. For more information, see Run an application.