Difference between revisions of "GPC Quickstart"
| Line 40: | Line 40: | ||
===MPI over Infiniband=== | ===MPI over Infiniband=== | ||
| − | To use the Infiniband interconnect for MPI communications, the | + | To use the Infiniband interconnect for MPI communications, the MVAPICH2 implementation |
has been installed and tested for both the intel V11 and GCC v4.1 compilers. | has been installed and tested for both the intel V11 and GCC v4.1 compilers. | ||
| + | |||
| + | Currently the only way to compile, link, and test an MPI code using MVAPICH2 is to use | ||
| + | an interactive queue session, using the os image "centos53develibA" as follows from a | ||
| + | GPC login-node. | ||
| + | |||
| + | <pre> | ||
| + | qsub -l nodes=2:ib:ppn=8,walltime=12:00:00,os=centos53develibA -I | ||
| + | </pre> | ||
| + | |||
| + | Once in the interactive session you will need to source one of the following to setup the appropriate | ||
| + | environment variables depending on if you want to compile with the intel or gcc compilers. | ||
Revision as of 11:30, 16 June 2009
| General Purpose Cluster (GPC) | |
|---|---|
|
File:Sunnyvale.jpg 200px | |
| Installed | June 2009 |
| Operating System | Linux |
| Interconnect | 1/4 on Infiniband, rest on GigE |
| Ram/Node | 16 Gb |
| Cores/Node | 8 |
| Login/Devel Node | gpc-login1 (142.150.188.51) |
| Vendor Compilers | icc (C) ifort (fortran) icpc (C++) |
| Queue Submission | LoadLeveller |
The General Purpose Cluster is an extremely large cluster (ranked Nth in the world, and fastest in Canada) and is where most simulations are done at SciNet. It is an IBM iDataPlex cluster based on Intel's Nehalem architecture (one of the first in the world to make use of the new chips). The GPC will consist of 3,780 nodes with a total of 30,240 2.5GHz cores, with 16GB RAM per node (2GB per core). One quarter of the cluster will be interconnected with non-blocking 4x-DDR Infiniband while the rest of the nodes are connected with gigabit ethernet.
Log In
The login node for the GPC cluster is gpc-login1.
Compile/Devel Nodes
Compilers
The intel compilers are icc/icpc/ifort for C/C++/Fortran. For MPI jobs, the scripts mpicc/mpicpc/mpifort are wrappers to the compilers which ensure the MPI header files and libraries are correctly included and linked to.
Submission Script
# # LoadLeveler submission script for SciNet GPC # don't know what goes here yet # Submit the job # #@ queue
MPI over Infiniband
To use the Infiniband interconnect for MPI communications, the MVAPICH2 implementation has been installed and tested for both the intel V11 and GCC v4.1 compilers.
Currently the only way to compile, link, and test an MPI code using MVAPICH2 is to use an interactive queue session, using the os image "centos53develibA" as follows from a GPC login-node.
qsub -l nodes=2:ib:ppn=8,walltime=12:00:00,os=centos53develibA -I
Once in the interactive session you will need to source one of the following to setup the appropriate environment variables depending on if you want to compile with the intel or gcc compilers.