You are here

Big Omics Data Engine (BODE)

The Big Omics Data Engine (BODE) Cray supercomputer, which consists of 2,484 Intel Haswell cores (and 5 petabytes of storage), is dedicated to NIH-funded Genomics-based research projects to maximally improve the computational throughput of the genomics data analysis workload and provide the storage space for large-scale data analysis.

The BODE system has:

  • 207 Cray CS300AC nodes, 13 Terabytes (TB) of memory
  • 2,484 Intel 2.4 GHz Haswell cores (12 / node)
  • 12 compute cores in 2 sockets with 6 cores on each socket and 64 Gigabytes (GB) of memory per node
  • 5 Petabytes (PB) of Data Direct Networks (DDN) SFA12KE storage connected via Infiniband

The BODE nodes are fully integrated into the Minerva computer complex and are available only to users with NIH-funded Genomics-based research projects.

All nodes are scheduled with LSF. There are no scavenger queues on BODE. Thus, all the jobs have to be submitted through one of allocation queues. The charging rate for the BODE nodes is 1.9X that for the AMD nodes. To force jobs onto the BODE partition, users should specify "-m bode" as a bsub option. If no "-m" option is used then the job will be scheduled to the first available node including a BODE node if the user is eligible.

The BODE system also includes a login node for eligible users, accessible by either login2.hpc.mssm.edu or bode.hpc.mssm.edu

As part of the BODE installation, two additional interactive nodes, interactive5 and interactive6, were added for the exclusive use of NIH funded researchers.

If you have an NIH-funded Genomics-related project and would like to run on BODE, then please let us know.

Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer