Texas Advanced Computing Center provides:
High performance computing systems- large clusters, capable of running highly parallel computation and advanced visualization.
Large data storage and data archival capabilities.
Software packages already installed on the clusters.
To find documentation/training on TACC systems: User guides, training courses offered by TACC and BCG.
Stuck with TACC specific errors or need a specific tool installed on TACC? Submit a ticket to TACC consulting.
Cluster systems are made up of multiple computers, connected together to act as one. Each computer is catwlled a node in the cluster and can have multiple processors (called cores). Users log in to the cluster through a limited number of login/head nodes and submit jobs to the many compute nodes. These systems are inherently parallel and can be greatly beneficial when your jobs are also parallelized.
LONESTAR6:
Reserved for UT faculty, staff and students
560 nodes (computers) with 128 cores per node
71, 680 cores (processors)
84 GPU nodes with 128 cores per node (for more computationally intensive tasks)
256 GB RAM
Max run time: 48 hours
USE: For running large, parallel computation jobs.
STAMPEDE3:
1060 SKX nodes (computers) with 48 cores (processors) per node, 560 SPR nodes (computers) with 112 cores (processors) per node, 224 ICX nodes (computers) with 80 cores per node
GPU nodes: 20 PVC nodes with 96 cores per node, 24 H100 GPU nodes with 96 cores per node
Max run time: 48 hours (without approval), 120 hours (with approval)
USE: For running large, parallel computation jobs
Frontera:
Fastest academic supercomputer in the country
USE: For running large, parallel computation jobs (particularly simulations and AI related tasks)
CORRAL:
Replicated storage
6 Petabytes of storage
Accessible on lonestar and stampede systems
$250 per terabyte (First 5 terabytes free for UT users)
USE: Backup data, analysis results.
RANCH:
Tape storage
Archival storage- not replicated or backed up.
60 Petabytes of storage
Immediate access can be difficult.
USE: Long term archival of data. One of two copies.
Now on to how to use the lonestar6 cluster...