Site Tools


tcr_hardware

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
tcr_hardware [2022/07/31 12:56] tmatejuktcr_hardware [2023/08/01 01:08] (current) – external edit 127.0.0.1
Line 2: Line 2:
   * CPU: 2x Intel(R) Xeon(R) CPU E5-2680 0 @ 2.70GHz (all)   * CPU: 2x Intel(R) Xeon(R) CPU E5-2680 0 @ 2.70GHz (all)
   * MEM: 64GB<sup>1</sup> (cnodes/gnodes)   * MEM: 64GB<sup>1</sup> (cnodes/gnodes)
-  * MEM: 512GB (mnodes)+  * MEM: 512GB<sup>2</sup> (mnodes)
   * GPU: Tesla K20m ( gnodes )   * GPU: Tesla K20m ( gnodes )
-  * NET: ethernet 1Gb, infiniband<sup>2</sup> (all)+  * NET: ethernet 1Gb, infiniband<sup>3</sup> (all)
  
  
Line 11: Line 11:
   * MEM: 500 GB   * MEM: 500 GB
   * NET: ethernet 1Gb   * NET: ethernet 1Gb
 +
 +storage :
 +  * shared, about 55 TB ( IBM store Wize family )
 +  * each node has about 800 GB of local hdd stata storage
  
  
Line 16: Line 20:
 ^ constrain name ^ nodes ^ ^ constrain name ^ nodes ^
 | intel | nodes with Intel processor | | intel | nodes with Intel processor |
-| gpu | nodes gpu +| gpu | gnodes nodes | 
-| bigmem | mnodes |+| bigmem | mnodes nodes |
 | ib | nodes with infiniband interface | | ib | nodes with infiniband interface |
 | power7 | pnode001 | | power7 | pnode001 |
Line 25: Line 29:
  
 <sup>1</sup>) on some nodes due to hardware errors available memory is less than 64GB, always use slurm's --mem, or --mem-per-cpu \\ <sup>1</sup>) on some nodes due to hardware errors available memory is less than 64GB, always use slurm's --mem, or --mem-per-cpu \\
-<sup>2</sup>) IB (infiniband) is not available on all nodes+<sup>2</sup>) on some nodes due to hardware errors available memory is less than 512GB, always use slurm's --mem, or --mem-per-cpu \\ 
 +<sup>3</sup>) IB (infiniband) is not available on all nodes
  
tcr_hardware.1659264976.txt.gz · Last modified: 2023/08/01 06:38 (external edit)