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)
11	PARAM Utkarsh,C-DAC,Bangalore	The PARAM UTKARSH is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 TeraFlops. This system is designed and implemented by the HPC Technologies Group, C-DAC at Banglore under National Super Computing Mission (NSM).2 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	458	641
12	Indian Institute of Technology (IITBHU),Varanasi	First Super Computer Installed by C-DAC under National Supercomputing Mission(NSM) Project. Atos BullSequana X series system with 192 cpu nodes, 20 High Memory nodes and 11 gpu nodes with 2xNvidia V100 16GB PCIe accelerator cards each having 5120 cuda cores.each node having 2xIntel Xeon Skylake 6148, 20 cores processors with CentOS Linux environment as OS.Primary Network Mellanox EDR Infiniband FatTree Interconnect.Lustre based primary,storage 750TiB usable with 25GB/Sec write throughput. Archival Storage 250TiB based on GPFS..first Super Computer installed by C-DAC under National Supercomputing Mission(NSM) project. It is based on a heterogeneous and hybrid configuration of BullSequana X400 series system with 192 CPU nodes, 20 High Memory nodes and 11 GPU nodes with 2xNvidia V100 accelerators. Each node having 2xIntel Xeon Skylake 6148, 20 cores processors with C-DAC Software stack. Primary Network Mellanox 100Gbps EDR Infiniband 100% fully non-blocking FatTree architecture. Lustre based primary storage 750TiB usable with 25GB/Sec write throughput. Archival Storage 250TiB based on GPFS. More Info OEM:Atos, Bidder:Atos	10176/2/223	456.9	645.12
13	Institute For Plasme Research(IPR),Ahmedabad	ANTYA HPC cluster consists of Acer hardware servers having 236 CPU-only nodes, 22 GPU nodes, 2 High Memory nodes and 1 Visualization node with Red Hat Enterprise Linux OS, and connected by 100Gbps Enhanced Data Rate (EDR) InfiniBand (IB) network. Total storage of 2 PB using GPFS file system. \|consists of Acer hardware servers having 236 CPU-only nodes, 22 GPU nodes, 2 High Memory nodes and 1 Visualization node with Red Hat Enterprise Linux OS, and connected by 100Gbps Enhanced Data Rate (EDR) InfiniBand (IB) network. Total storage of 2 PB using GPFS file system More Info OEM:Acer, Bidder:Locuz	9440//	446.9	724.992
14	Aeronautical Development Agency, DRDO,Bangalore	256 node Dual Intel Skylake with 20 core processor at 2.0 GHz w/ EDR Infiniband256 node Dual Intel Skylake with 20 core processor at 2.0 GHz w/ EDR Infiniband More Info OEM:Dell, Bidder:Dell	259//	437	655
15	PARAM Ananta,IIT Gandhinagar,Ahmedabad	The PARAM Ananta is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 Tera Flops. This system is designed and implemented by the HPC Technologies Group, C-DAC at IIT Gandhinagar under National Super Computing Mission (NSM).2 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	434.5	681.5
16	NABI,Mohali	The PARAM SMRITI is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 TeraFlops. This system is designed and implemented by the HPC Technologies Group, C-DAC at NABI,Mohali under National Super Computing Mission (NSM).2 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	429	641
17	Indian institute of Technology,HYderabad	The PARAM SEVA is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 TeraFlops. This system is designed and implemented by the HPC Technologies Group, C-DAC at IIT,Hyderabad under National Super Computing Mission (NSM).2 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	428	641
18	PARAM Himalaya,Mandi	The PARAM Himalaya is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 Tera Flops. This system is designed and implemented by the HPC Technologies Group, C-DAC at IIT Mandi under NSM.2 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	428	641
19	PARAM Porul,Tiruchirappalli	The PARAM Porul is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 Tera Flops. This system is designed and implemented by the HPC Technologies Group, C-DAC at NIT Tiruchirappalli under NSM1 More Info OEM:ATOS, Bidder:ATOS	7488/2/156	427	641
20	PARAM Kamrupa,Guwahati	The PARAM Kamrupa is a heterogeneous and hybrid configuration of Intel Xeon Cascade Lake processors, NVIDIA Tesla V100 with NVLink, Mellanox HDR interconnect with C-DAC HPC Software stack having peak capacity of 838 Tera Flops. This system is designed and implemented by the HPC Technologies Group, C-DAC at IIT Guwahati under NSM.2 More Info OEM:ATOS, Bidder:ATOS	15120/2/315	427	641

,