Olympus is a flexible, multiple-use compute cluster dedicated to research in the MIDAS community.
Olympus comprises several specialized partitions to accommodate a variety of workloads including: extremely high memory multi-threaded applications, tightly coupled message-passing applications, and trivially-parallel (or serial) batch jobs.
The Olympus cluster consists of 23 execution hosts (i.e. nodes) and an additional 'head node' which runs system services, exports the network filesystem and hosts several virtualized login nodes.
Each node has four multi-core processors and each processor has 16 compute cores, for a total of 64 compute cores per node and 1536 compute cores overall. Eight of the nodes each have 512 GB of aggregate memory, and the other 15 each have 256 GB, for a total of 7.5 TB of aggregate memory. Each node runs a 64-bit CentOS 6 operating system and all nodes are connected to one another by Gigabit Ethernet. There is a 2TB shared filesystem that is available on all nodes, and each node has locally mounted disk space.