We’re working with multiple project owners to migrate their workloads from Andromeda 1 to Andromeda 2 at this time. Each new group that migrates takes a bit of compute with them from Andromeda 1 to Andromeda 2, until eventually Andromeda 1 is no more and only Andromeda 2 remains. So, you may notice Andromeda 1 has fewer compute nodes. But, don’t worry, there are also fewer workloads being run there!
We’re being as conservative as possible with how many resources get migrated, we don’t want to create a bottleneck for researchers on either cluster. And we’ll be adding the next round of compute nodes being purchased directly to Andromeda 2. A few new big memory nodes and GPU nodes are being added to meet the cluster community’s growing demands and help balance out the migration needs in the coming months.
Please be patient with queue times and resource availability till only one Andromeda remains. But, if you do have a deadline or an urgent need for cluster resources, please don’t hesitate to contact us via our Research Help request form.