Param Pravega VS all other supercomputers

The Indian Institute of Science, Karnataka, claimed to have launched India’s most powerful supercomputer, Param Pravega. As of 2020, India has two supercomputers, PARAM Siddhi-AI and Mihir, which are listed in the Top 500 Global Supercomputers, ranking 63rd and 146th respectively. Param Pravega, with his claims, could possibly beat these computers by being India’s most powerful supercomputer. But is it true?

Analytics India Magazine explores Param Pravega’s position against India’s and the world’s top supercomputers.

About the supercomputer

Param Pravega is designed by the Center for Development of Advanced Computing with most components being made in India. It is set up as part of the National Supercomputing Mission which aims to equip Indian academic institutions with supercomputing networks in more than 70 HPC facilities. The machine is a resource for running high performance computing applications as well as hosting various tools and libraries. Considering this feature, Param Parvega has been taken advantage of by all; faculty members, students, and researchers at the institution for studies on COVID-19, modeling viral entry, studying proteins, green energy technologies, climate change, etc.

Currently, ten of these supercomputers have been deployed at IISc, IISER, IIT, JNCASR, C-DAC and NABI-Mohali, providing approximately 3,100,000 computing jobs and enabling 2,600 cross-national research. The supercomputer falls under the government’s National Knowledge Network program which links universities, research and development labs over a high-speed network.

The software stack
Param Pravega has a total supercomputing capacity of 3.3 petaflops, with all ten supercomputers totaling up to 17 petaflops. The software runs on a CentOS 7.x distribution based on the Linux operating system with two master nodes, 11 connection nodes, two firewall nodes, four management nodes, one NIS slave and 624 compute nodes (CPUs +GPUs). These are further divided into regular CPU nodes, high memory CPU nodes, and GPU nodes. Intel Xeon Cascade Lake processors are used for CPU nodes and NVIDIA Tesla V100 cards are used on GPU nodes. A FAT-tree topology with a 1:1 subscription ratio and 4 petabyte parallel storage connects the nodes and provides parallel file system access.

Param Pravega compared to the world’s best supercomputers

By comparison, India’s PARAM Siddhi, 63rd on the Top 500 list, achieved several performance benchmarks, including 4.6 petaflops in sustained double accuracy, 6.5 petaflops in maximum double accuracy and 210 petaflops in total AI. . It was built on NVIDIA DGX SuperPOD reference architecture networking and C-DAC’s locally developed HPC-AI engine. The DGX SuperPOD reference architecture is known for providing blueprints for assembling world-class infrastructure and powerful supercomputers.

The Indian Institute of Tropical Meteorology’s Pratyush weather forecasting supercomputer ranked 78th in the November edition of the list. Along with Pratyush, Mihir, another noted supercomputer on the list, is a 2.8 petaflops machine. Together, Pratyush and Mihir consist of multiple computers capable of delivering a peak power of 6.8 PetaFlops, making it the first multi-PetaFlops supercomputer ever built in India. Pratyush and Mihir are employed for weather forecasting and climate monitoring, accurately predicting monsoon, fishing, air quality and catastrophic events such as tsunamis, cyclones, earthquakes, lightning, floods, droughts and other natural calamities. India is the fourth company after Japan, the United States and the United Kingdom to have a dedicated high performance computing facility for weather and climate research.

NVIDIA Cambridge-1, the UK’s top supercomputer, also runs on the NVIDIA DGX SuperPOD cluster. Additionally, the stack consists of NVIDIA A100 GPUs, BlueField-2 DPUs, and NVIDIA HDR InfiniBand networking, which add up to deliver 8 petaflops of performance and 400 petaflops of AI performance.

The world’s fastest supercomputer, Fugaku, reported an initial Rmax performance of 416 petaFLOPS in the FP64 high-performance LINPACK benchmark. However, after last year’s upgrade, Fugaku’s performance increased to an Rmax of 442 petaFLOPS.

Pangea III – the world’s most powerful commercial supercomputer built by IBM, has a computing power of 25 petaFLOPS, with a storage capacity of 50 petabytes. It’s built on IBM POWER9 AI, the company’s high-performance architecture with industry-exclusive technology to handle massive data loads.

Recently, Meta introduced its AI Research SuperCluster (RSC) supercomputer in collaboration with NVIDIA. It uses 760 NVIDIA DGX A100 systems and consists of 6,080 NVIDIA A100 GPUs bonded over an NVIDIA Quantum 200 Gb/s InfiniBand network delivering 1,895 petaflops of TF32 performance.

IISc’s track record in supercomputers is impressive. Their SahasraT was the fastest supercomputer in India in 2015 and has been used by faculty and students for impactful research studies ever since. Param Pravega, with its claims, assures a similar productivity promise.

About Mariel Baker

Check Also

AMD Releases Latest Consistent Device Memory Mapping Linux Code – Designed for Frontier

Over the past year, we have seen various patches released by AMD engineers with a …