Facilities
HCC supports a diverse collection of hardware that is here as a campus resource, and anyone on campus is welcome to apply for an account on these machines.
Access to these resources is by default shared with the rest of the user community via various job schedulers. These policies may be found on the pages for the various resources. Alternatively, a user may buy into an existing resource, acquiring 'priority access'. Finally, several machines are available via Condor for opportunistic use. This will allow users almost immediate access, but the job is subject to preemption.
Click the 'New Users' link on the navigation bar to register now!
Computers
Tusker - HCC's newest machine, Tusker consists of 106 AMD Interlagos-based nodes (6784 cores) interconnected with Mellanox QDR Infiniband.
Firefly - 5600 core AMD cluster located at PKI.
PrairieFire - 90 AMD processor machines packed together into a small space make for one hot cluster. It also makes up our beloved PrairieFire.
and
Sandhills - has 1440 AMD cores housed in 42 nodes with 128GB per node and 2 nodes with 256GB per node.
Red - This cluster is the resource for UNL's US CMS Tier-2 site. It consists of ~2500 Condor job slots and ~2 PB of raw storage.
Merritt - An SGI Altix 3700 supercomputer purchased for general use by UNL researchers.
Overview
Cluster |
Overview |
Processors |
RAM |
Connection |
Storage |
|
Firefly
|
1,151 node production-mode LINUX cluster |
871 (2.8 GHz , 64 bit) Opteron, 4-Core Per Node 280 2.2 GHz, 8-Core Per Node |
8 GB per node |
800 MB/sec Infiniband interconnect |
150 TB shared Panasas storage 6 TB SATA RAID 73 GB per node |
|
PrairieFire
|
90 Node Production-mode LINUX cluster |
2 Opteron 248 2 Opteron 275 8 Opteron 870 (2.2GHz/64 bit) per node |
minimum of 4 GB PC2700 per node |
Infiniband Myrinet (2 Gb/s) Gigabit Ethernet |
1 TB SCSI RAID (XFS over NFS) 6 TB SATA RAID (ReiserFS over NFS) 20 GB per node |
|
Sandhills
accessible through PrairieFire Scheduler |
44 Node Production-mode LINUX cluster |
1344 cores 2.2 GHz AMD Opteron 6128 96 cores at 1.9GHz AMD Opteron 6168 |
42 Nodes with 128GB per node 2 Nodes with 256GB per node |
QDR Infiniband Gigabit Ethernet |
~1.5TB per node |
|
Red
|
266 node Production-mode LINUX cluster |
40x Opteron 2261 70x Opteron 2354 43x Xeon E5520 40x Xeon E5530 ~2500 Condor job slots |
1.5-2GB RAM per job slot |
Gigabit Ethernet |
~2 PB of raw storage space |
Merritt |
Developmental, Production Mode Research Shared Memory Platform. |
64 1.3 GHz Itanium |
512 GB Shared Memory |
SGI NUMAlink-3 Dual-plane, fat-tree topology |
8 TB Fibre-Channel attached RAID |
|
Tusker
|
106 node Production-mode LINUX cluster |
Opteron 6272 2.1GHz, 4 CPU/64 cores per node |
256 GB RAM per node |
QDR Infiniband |
~350 TB shared Lustre storage ~500GB local scratch |
