Run RocHPCG Singularity Application

This guide shows how to run the RocHPCG Singularity application. Sign in to AAC if you have not already.

Select application

Click Applications, then select HPCG.

Select container

Select the RocHPCG version with container type singularity.

Note

In this example we use rocHPCG 3.1.0_97 with singularity.

New workload

Click New Workload at the top right.

Select team

If you have more than one team, select one in the pop-up and click Launch. Click Next to continue.

Select resources

Click Next to use the default script (for 8 GPUs): mpirun --mca pml ucx -np 8 hpcg 280 280 280 1860.

Select the allowed run time. The number of GPUs should be 8. Here, we have selected the run time as 1 hour, number of GPU’s as 8 and telemetry is enabled.Click on Next button.

Note: The time for which workload is allowed to run should be specified in the Maximum allowed runtime field. By default 1 hour will be selected.

If maximum allowed run time is 1 hour, it implies, workload will run for 1 hour and then it will be automatically stopped after 1 hour as it will not be allowed to exceed Maximum allowed runtime.

Based on the time required for workload, user should change the Maximum allowed runtime. Once workload is launched, user cannot change the total workload time. It has to be configured in the current step.

Select compute

Select the cluster and queue for the job, then click Next.

Review workload submission

Review the configuration and click Run Workload.

Monitor workload

When the run finishes, the status is Completed. Use the STDOUT and STDERR tabs for logs; the Performance tab shows telemetry. The final score in STDOUT is the RocHPCG performance.