Raijin, named after the Shinto God of thunder, lightning and storms, is a Fujitsu Primergy high-performance, distributed-memory cluster, procured with funding from the Australian Government, through its Super Science Initiatives, under the EIF Climate HPC Centre Funding Agreement between the Commonwealth of Australia and the Australian National University.
The system was installed in 2012 and entered production use in June 2013. It comprises:
- 57,864 cores (Intel Xeon Sandy Bridge technology, 2.6 GHz) in 3602 compute nodes
- 56 NVIDIA Tesla K80 GPUs
- 162 TBytes of main memory
- Mellanox FDR 56 Gb/sec Infiniband full fat tree interconnect
- 12.5 PBytes of high-performance operational storage capacity
This provides a peak performance of approximately 1.37 PFlops
The unit of shared memory parallelism is the node, which comprises dual 8-core Intel Xeon (Sandy Bridge 2.6 GHz) processors, i.e., 16 cores.
The memory specification across the nodes is heterogeneous in order to provide a configuration capable of accommodating the requirements of most applications, and providing also for large-memory jobs. Accordingly:
- Two-thirds of the nodes have 32 GBytes, i.e., 2 GBytes/core;
- Almost one-third of the nodes have 64 GBytes, i.e., 4 GBytes/core; while
- Two (2) per cent of the nodes have 128 GBytes, i.e., 8 GBytes/core.
The Raijin system is configured with:
- OneSIS cluster manager
- PBS Professional job scheduler.