Top Supercomputers- India

January2023

Following is the ranking of the systems in terms of Rmax (Linpack Benchmark performance).

C - CPUs, G-GPUs, ICO - Intel Co-processors. Cores (4th column) that are not qualified with C/G/ICO refer to CPUs.
OEM - Original Equipment Manufacturer, SI - System Integrator.

Rank	Site	System	Core/Processor/Socket/Nodes	Rmax (TFlops)	Rpeak (TFlops)
61	National Institute of Technology,Raipur	Fujitsu Server PRIMERGY RX2530 M2 One Master node with 54 Compute Nodes/12core per Sockets with Dual E5-2680 V4@ 2.10Ghz processor 128GB RAM connected with Intel OmniPath 100GbpsPRIMERGY RX2530 M2 Master node with 54 Nodes/12core per Sockets with Dual E5-2680 V4@ 2.10Ghz processor 128GB RAM connected with Intel OmniPath 100Gbps More Info OEM:Fujitsu, Bidder:Wizertech	1296//54	39.5	45.6
62	Centre for Modeling and Simulation, Pune University,Pune	IASRI-Delhi 256 Node HPC cluster based on HP SL390 G7 nodeIntel Xeon E5-2697 @ 2.6GHz dual fourteen-core CPU nodes More Info OEM:Fujitsu, Bidder:Locuz	1344/2/48	39.29	55.91
63	C-DAC,Pune,	100TF HPC system based on the A64FX ARM processor, Mellanox HDR as an interconnect with C-DAC HPC Software stack. This system is designed and implemented by the HPC Technologies Group at C-DAC Pune under National Super Computing Mission (NSM)Mellanox 100Gbps InfiniBand Switch for Primary communication More Info OEM:HPE, Bidder:SS Information Systems Pvt Ltd .	720//16	39	57
64	National Institute of Science Education and Research(NISER),Bhubaneswar	Hartree cluster is a HPC of 40 compute nodes and 2 master nodes in HA configuration. It is based on Intel(R) Xeon(R) CPU E5-2697A v4 @ 2.60GHz. Two sockets for each node (32-cores per node) on Supermicro SuperServer SYS-6028R-TR with 64 GB of RAM per nodeof 40 compute nodes and 2 master nodes in HA configuration with FDR 56Gbps Interconnect and 230TB Storage in Lustre parallel file system. More Info OEM:Netweb, Bidder:Netweb	1344//	38.87	51.9
65	Space Applications Centre (SAC), ISRO,Ahmedabad	The HPC System named as AKASH is equipped with two Master Nodes with High Availability, 36 Compute Nodes (only CPU) & 2 Hybrid nodes (CPU+ Xeon Phi). it offers 1,368 CPU cores, 244 Xeon Phi Cores, ~10 TB of RAM, 40 TB usable of High Performance Parallel Lustre File System and 120 TB Archival Storage.Intel Xeon E5-2699v3 @2.3 GHz dual eighteen-core processor nodes) w/Infiniband 4x FDR Interconnect More Info OEM:HP, Bidder:TCS	1368 + 244/2/	36.67	50.34
66	Indian Institute of Science Education and Research,Bhopal	IBM System x iDataPlex with 132 dx360 M4 Server as Compute Nodes, 2112 cores, 9.2 Terabytes of total memory, w/Infiniband QDR, fully non-blocking FAT tree. 50 GB Usable Capacity Storage based on IBM General Parallel File System over 2 x IBM DS3534 Storage System.Intel(R) Xeon(R) CPU E5-2670 @ 2.6 GHz dual octo-core processor nodes w/Infiniband More Info OEM:IBM, Bidder:	2112/2/	35.36	43.92
67	Center For Developement of Advanced Computing(CDAC),Pune	CDAC HPC is of 100 TF built with 16 CPU only nodes and 4 GPU V100 nodes cluster using AMD EPYC ROME Processor. 240 TB of Lustre PFS with 5.7 Gbps performance. EDR Interconnectis of 100 TF built with 16 CPU only nodes and 4 GPU V100 nodes cluster using AMD EPYC ROME Processor. 240 TB of Lustre PFS with 5.7 Gbps performance. EDR Interconnect More Info OEM:HPE, Bidder:Concept IT	1024//	29.4	40.96
68	Centre for Development of Advanced Computing (C-DAC),Pune	The Trinetra test cluster consists of 12compute nodes having peak computing capacity of 10.6 TFlops. Each node has Intel Xeon Skylake processors (Gold 5118, 24C, 2.3 GHz) and 96 GB memory. The cluster is build using C-DAC’s indigenously developed Trinetra interconnect. Trinetra is 3D-Torus based interconnect. This system is designed and implemented by the HPC Technologies Group, C-DAC under National Supercomputing Mission (NSM).2 More Info OEM:Supermicro, Bidder:Netweb Technologies	288/2/12	7.87	10.59

,