New Delhi, Dec 30, 2014: The Centre for Development of Advanced Computing (C-DAC) has unveiled what it claims is the world’s most compact supercomputing system today.
This new High Performance Computing solution christened PARAM Shavak is a ready-to-use affordable supercomputer pre-loaded with all the required system software and applications from selected scientific and engineering domains. The system is designed to be enabling tool for research organizations as well as academic institutions that need HPC for education and research. It aims to provide computational resource with advanced technologies at affordable cost to perform the high-end computations for the scientific, engineering and academic programmes to address and catalyze the research using modelling, simulation and data analysis.
It was launched here on Christmas Day by Indian Minister for Communications & IT Ravi Shankar Prasad.
Said Rajat Moona, Director General, C-DAC: "Param Shavak is the perfect compromise between high performance computing requirements and infrastructure availability. The compact nature of its design makes it an ideal solution for multiple environments both for research as well as for training. We are hopeful that the research and academic institutes will see the potential of this tool to ramp up their in-house research and scale new challenges. Our primary aim is to enhance the HPC ecosystem in the country through the use of PARAM Shavak and raise the bar of R&D in the country”.
Added Sanjay Wandhekar, Associate Director & Head, High Performance Computing , C-DAC, Pune: "Param Shavak could be placed in a standard office workspace. It comes with a handful of value additions from C-DAC viz. indigenously developed software with most of the features that can be found in a full blown HPC clusters like job schedulers, compilers, parallel libraries, MPI, resource managers, some of the commonly used HPC applications in engineering and scientific domains, etc”.
The system consists of at least 2 multicore CPUs each with at least 10 cores along with either one or two number of many core or GPU accelerator cards. The entire configuration is available in a single server in a table top model. Regardless to the traditional HPC systems/supercomputers, this system does not require specific support infrastructure like precision air-conditioned environment, controlled humidity etc.