Compute Info


Compute Node Information


PRATYUSH is running on 3315 Intel Xeon Broadwell E5-2695 v4 2.1GHz 18C CPU on its login and compute nodes. It has 2 CPUs per node with a total of 36 cores per node.Each compute node contains 128GB DDR4 .

 


Accelerated Node


The system has 16 accelerator nodes powered with Intel KNL 7210 processors , 96 GB DDR4 per node with a total Peak Performance of 42.56 TFLOPS.

 

 


Interconnect


XC40 compute nodes are connected using Cray Aries Network On Chip.The four nodes in a blade communicates through the Aries Chip.

Sixteen blade in a chassis are connected through the Aries chip onto a backplane. Each Cabinet consists of three chassis and two cabinets forms a group. All six chassis in a group are connected in all-to-all manner using electrical cables with data transfer rate of 14Gbps. All four groups of the Cray system are connected using optical cables with a data transfer of 12.5 Gbps.

 


Operating System


The system runs Cray Linux Environment(CLE) which is Cray’s customised version of the SUSE Linux Enterprise Server 12.2

CLE consists of two components: CLE and Compute Node Linux (CNL). The service nodes, external login nodes, and post-processing nodes of Cray XC40 run a full-featured version of Linux.

 

 


Research And Developement System


Research and Development system is a 48 node cluster which has 23 CPU nodes, 16 GPU nodes with direct attached lustre filesystem, 8 service nodes and PBS Pro scheduler.

Compute nodes:
The system has 23 CPU nodes powered with Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz processor, 192 GiB DDR4-2666 w/ Chipkill TM technology memory. It has 2 CPUs per node with a total of 40 cores per node.

GPU nodes:
The system has 16 accelerator nodes powered with Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz processor, 64 GiB DDR4-2400 w/ Chipkill TM technology memory , 1 Tesla P100 with memory of 12 GiB.It has 1 CPU per node with a total of 36 cores/node.


Storage:
The system has Cray Direct attached lustre with an usable space of 349TB with a throughput of 4.7GB/s.

 

 


Additional Nodes


There are 5 external nodes which are used for submitting job into the cluster.

There are 8 utility nodes which are used for  pre/post processing of the code and visualization purpose .