Difference between revisions of "BGQ"
Line 7: | Line 7: | ||
|nnodes= 2048(32,768 cores), 512 (8,192 cores) | |nnodes= 2048(32,768 cores), 512 (8,192 cores) | ||
|rampernode=16 Gb | |rampernode=16 Gb | ||
− | |corespernode=16 ( | + | |corespernode=16 (64 threads) |
|interconnect=5D Torus (jobs), QDR Infiniband (I/O) | |interconnect=5D Torus (jobs), QDR Infiniband (I/O) | ||
|vendorcompilers= bgxlc, bgxlf | |vendorcompilers= bgxlc, bgxlf | ||
Line 16: | Line 16: | ||
===Specifications=== | ===Specifications=== | ||
− | + | ||
+ | BGQ is an extremely powerful and energy efficient 3rd generation IBM Supercomputer built around a system on a chip compute node that has a 16core 1.6GHz Power based CPU and | ||
+ | 16Gb of Ram and runs a very lightweight Linux OS called CNK. The nodes are bundled in groups of 32 and then 16 of these groups make up a midplane with 2 midplanes per | ||
+ | rack. The compute nodes are all connected togther using a custom 5D interconnect. Each midplane has 8 Power7 I/O nodes that run a full Redhat Linux OS that manages | ||
+ | the compute nodes and mounts the GPFS filesystem. | ||
=== Jobs === | === Jobs === | ||
+ | |||
+ | BGQ job size is typically determined by midplanes (512 nodes or 8192 cores), however sub-blocks can be used to further subdivide midplanes with a minimum of | ||
+ | one IO node per block. In SciNet's configuration (with 8 I/O nodes per midplane) this allows 64 nodes (1024 cores) to be the smallest job size. | ||
+ | |||
+ | |||
=== I/O === | === I/O === | ||
− | + | GPFS |
Revision as of 14:34, 18 August 2012
Blue Gene/Q (BGQ) | |
---|---|
Installed | August 2012 |
Operating System | RH6.3, CNK (Linux) |
Number of Nodes | 2048(32,768 cores), 512 (8,192 cores) |
Interconnect | 5D Torus (jobs), QDR Infiniband (I/O) |
Ram/Node | 16 Gb |
Cores/Node | 16 (64 threads) |
Login/Devel Node | bgq01,bgq02 |
Vendor Compilers | bgxlc, bgxlf |
Queue Submission | Loadleveler |
Specifications
BGQ is an extremely powerful and energy efficient 3rd generation IBM Supercomputer built around a system on a chip compute node that has a 16core 1.6GHz Power based CPU and 16Gb of Ram and runs a very lightweight Linux OS called CNK. The nodes are bundled in groups of 32 and then 16 of these groups make up a midplane with 2 midplanes per rack. The compute nodes are all connected togther using a custom 5D interconnect. Each midplane has 8 Power7 I/O nodes that run a full Redhat Linux OS that manages the compute nodes and mounts the GPFS filesystem.
Jobs
BGQ job size is typically determined by midplanes (512 nodes or 8192 cores), however sub-blocks can be used to further subdivide midplanes with a minimum of one IO node per block. In SciNet's configuration (with 8 I/O nodes per midplane) this allows 64 nodes (1024 cores) to be the smallest job size.
I/O
GPFS