Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
en:services:application_services:high_performance_computing:running_jobs_for_experienced_users [2018/11/14 16:05]
[Nodes' specification] removed gwdc, gwdb and partially gwda nodes
en:services:application_services:high_performance_computing:running_jobs_for_experienced_users [2018/11/14 16:06] (current)
[Nodes' specification] removed tp info
Line 25: Line 25:
 GTX nodes are for single precision CUDA applications and K40 nodes for double precision or memory intensive CUDA applications. GTX nodes are for single precision CUDA applications and K40 nodes for double precision or memory intensive CUDA applications.
  
-Finally there are 40 ''​tp''​ (for ''​throughput''​) nodes with 64 AMD cores and 64 GB of memory.  +The ''​mpi''​ nodes provide the bulk of the compute power of our compute cluster and are meant for all types of applications. They are especially well suited for large MPI jobs, as they have a balanced compute to network performance ratio. The ''​fat''​ nodes are meant for shared memory parallelized workloads scaling beyond 16 cores, and for all applications requiring more than 64 GB of memory on a single node.
- +
-The ''​mpi''​ nodes provide the bulk of the compute power of our compute cluster and are meant for all types of applications. They are especially well suited for large MPI jobs, as they have a balanced compute to network performance ratio. The ''​fat''​ nodes are meant for shared memory parallelized workloads scaling beyond 16 cores, and for all applications requiring more than 64 GB of memory on a single node. The ''​tp''​ nodes are not meant for general usage, as they are not owned by GWDG.+
  
 ===== Interactive session on the nodes ===== ===== Interactive session on the nodes =====