How can HPC speed up my simulations?
Lumerical Products are not only capable of utilizing all of your workstations resources to the fullest, but they can also utilize the resources of multiple machines (a cluster) to drastically reduce your time-to-results. There are two main ways that a cluster can be utilized to speed up your simulations (as well as a 3rd hybrid configuration):
1. Concurrent Computing: Running multiple simulations in parallel (ie. sweeps and optimizations).
2. Distributed Computing: Running a single simulation, spread across a cluster (FDTD and varFDTD).
How can I get started with HPC?
Cloud computing is a great way to evaluate new hardware before purchasing, or as a long term solution that is highly scale-able, low maintenance, no-cost investment. Following our AWS quick-start guides, you can easily start running your simulations in the cloud within a day. These guides will help you identify the type and amount of computing resources necessary for your workload.
- AWS quick-start guides
- Use Case: Single Workstation
- Use Case: Multi-node clusters with launch templates
- Use Case: Auto-Scaling Cluster (AWS ParallelCluster, QSUB)