Demonstrating Performance Capabilities of Red Hat OpenShift for Running Scientific HPC Workloads
2020-11-11 in WorkToday, we’ve published the work I’m done in cooperation with David Gray on the performance evaluation of running scientific HPC applications on OpenShift.
- Demonstrating Performance Capabilities of Red Hat OpenShift for Running Scientific HPC Workloads
- PDF archive
This blog post is a follow-up to the previous blog post on running GROMACS on Red Hat OpenShift Container Platform (OCP) using the Lustre filesystem. In this post, we will show how we ran two scientific HPC workloads on a 38-node OpenShift cluster using CephFS with OpenShift Container Storage in external mode. We will share the benchmarking results of MPI Microbenchmarks, GROMACS, and SPECFEM3D Globe. We ran these workloads on OpenShift and compared them against the results from a bare-metal MPI cluster using the same hardware.
