Systems

Kohinoor 5

 

Computing Capicity – 98.92 TF

CPU Node – 35 [96C / Node]

Kohinoor 5 is the fifth HPC cluster in the Kohinoor tetralogy of clusters in TIFR, Hyderabad with a real-time peak computing capacity of 98.92 TF, which was installed and operational from June 2023.
This cluster is composed of 35 nodes, in which one of them are login node / master node and all the other are execution nodes. This cluster is composed of 35 CPU nodes with 96 cores per node. The cluster nodes are connected together through a completely non-blocking 10 Gigabit switch. The cluster is managed by the open-source batch scheduler “PBS Pro” software for job scheduling and load balancing. The login node allows user logins for job submission in the cluster. The cluster has a locally attached ZFS File System of 380 TB across the nodes through 10G switch, which is used for computational runs

Kohinoor 5 Cluster Documents

Kohinoor 4

Computing Capicity – 124.9 TF

CPU Node – 88 [32C / Node]

Kohinoor 4 is the fourth HPC cluster in the Kohinoor tetralogy of clusters in TIFR – TCIS, Hyderabad with a real-time peak computing capacity of 124.9 TF, which was installed and operational from May 2019. This cluster is composed of 90 nodes, in which two of them are head nodes and all the other are execution nodes. This cluster is composed of 88 CPU nodes with 32 cores per node. The cluster nodes are connected together through a completely non-blocking Intel OmniPath (OPA) switch. The cluster is managed by the open source batch scheduler “PBS Pro” software for job scheduling and load balancing. The head-node allows user logins for job submission in the cluster. The cluster has a locally attached ZFS File System of 200 TB connected across the nodes through OPA switch, which is used for computational runs and another 400 TB ZFS storage is attached to the secondary head node of the cluster for the purpose of archiving and post-processing of data.

Kohinoor 4 Cluster Document

Kohinoor 3

Computing Capicity – 43.51 TF

CPU Node – 64 [20C / Node]

GPU Node – 4 [4 Nvidia Tesla K40 / Node ]

Interconnect – 56Gbps IB

Kohinoor 3 is the third HPC cluster in the Kohinoor tetralogy of clusters in TIFR – TCIS, Hyderabad with a real-time peak computing capacity of 43.51 TF, which was installed and operational from September 2016.
This cluster is composed of 69 nodes, in which one is a head node and all other are execution nodes. This cluster is a heterogeneous cluster which is composed of 64 CPU nodes with 20 cores per node and 4 GPU nodes with 4 Nos of Nvidia Tesla K40 per node. The cluster nodes are connected together through a completely non-blocking Mellanox FDR Interconnect InfiniBand (IB) switch. The cluster is managed by the open source batch scheduler “PBS Pro” software for job scheduling and load balancing. The head-node allows user logins for job submission in cluster. The cluster has a locally attached Parallel File System (Open source Lustre) of 200 TB connected across the nodes through IB switch, which is used for computational runs and another 200 TB NAS is attached to the head node of the cluster for the purpose of archiving and post-processing of data.

Kohinoor 3 Cluster Document

Kohinoor 2

Computing Capicity – 9.95 TF

CPU Node – 32 [16C / Node]

Interconnect – 40Gbps IB

Kohinoor 2 is the second High Performance Computing (HPC) cluster in the Kohinoor tetralogy of clusters installed at TIFR-TCIS Hyderabad with a real-time peak computing capacity of 9.95 TF. This cluster is composed of 33 nodes, in which one is a head node and all other are execution nodes. This cluster is composed of 1 head node, 32 CPU nodes with 16 cores per node and 50 TB NAS storage. The cluster nodes are connected together through a completely non blocking Intel truscale QDR Interconnect infiniband (IB) switch. The cluster is managed by the open source batch scheduler “Open Grid Engine” software for job scheduling and load balancing. The head-node allows user logins for job submission in cluster. The cluster has a local Network Attached Storage (NAS) of 50 TB connected across the nodes through IB switch, which is used for computational runs.

Kohinoor 2 Cluster Document

Kohinoor 1

 

Computing Capicity – 4.42 TF

CPU Node – 12 [16C / Node]

GPU Node – 4 [2 Fermi M 2090 / Node ]

Interconnect – 40Gbps IB

Kohinoor 1 is the first High Performance Computing (HPC) cluster in the Kohinoor tetralogy of clusters installed at TIFR-TCIS Hyderabad with a real-time peak computing capacity of 4.42 TF. This cluster is composed of 17 nodes, in which one is a head node and all other are execution nodes. This cluster is a heterogenous cluster which is composed of 12 CPU nodes with 16 cores per node and 4 CPU nodes with 2 Fermi M 2090 GPUs per node. The cluster nodes are connected together through a completely non blocking Mellanox QDR Interconnect infiniband (IB) switch. The cluster is managed by the open source batch scheduler “Open Grid Engine” software for job scheduling and load balancing. The head-node allows user logins for job submission in cluster. The cluster has a local Network Attached Storage (NAS) of 40 TB connected across the nodes through IB switch, which is used for computational runs and a 36 TB NAS is attached to the head node of the cluster for the purpose of archiving and post-processing of data.

Kohinoor 1 Cluster Document