Hardware

Bigram2 is intended for jobs that cannot be parallelized and require a large amount of RAM memory, such as de novo genome assembly.

Biocrunch2 is a shared computing resource for those who need multithreaded computation but are not yet prepared to use a traditional HPC cluster, or need more flexibility than is provided through the cluster scheduler.

Biocrunch4 is a shared computing resource for those who need multithreaded computation but are not yet prepared to use a traditional HPC cluster, or need more flexibility than is provided through the cluster scheduler.

Biocrunch6 is a shared computing resource for those who need multithreaded computation but are not yet prepared to use a traditional HPC cluster, or need more flexibility than is provided through the cluster scheduler.

Biocrunch8 is a shared computing resource for those who need multithreaded computation but are not yet prepared to use a traditional HPC cluster, or need more flexibility than is provided through the cluster scheduler.

In addition to the compute nodes, the Condo2017 cluster also contains a "huge" memory node

The Condo2017 Free Tier is composed of 48 nodes from the cluster previously named ClusterOne, and prior to that named LHB-NGS and LHB-PS.  This cluster is running the RISA software repository, and is a good place to run MPI capable programs.

These nodes are slightly older than the regular compute nodes in the Condo cluster, and the processors are not as fast. This tier is being made available to any research group in the University as a way to become introduced to the HPC environment without an upfront cost commitment. 

Please email researchit@iastate.edu to obtain access.

This server contains 8 Nvidia 1080Ti GPUs and is meant for running code that has been compiled to run on a GPU, using a tool such as CUDA, OpenMP, OpenACC, etc.

The type of applications commonly run on this server are cryoEM, deep learning, and molecular dynamics.

The Legion servers are best for problems which can be highly parallelized (particularly where each thread is doing something slightly different from the others).  Each legion node has a very large number of cores available, but those cores are slower than those found on a typical Intel Xeon processor like you'll find on our other servers. Due to the large number of cores, these servers are faster at processing particular types of workloads such as molecular dynamics, genome alignment, and monte carlo simulations.

We have 8 Legion servers behind a head node running the SLURM job scheduler. Each node has 272 threads available, and 384GB of RAM.