HPC in Marine Research & Development activities


Marine Research organization improved speed of execution of their various R&D experiments by harnessing Fujitsu's High Performance Computing (HPC) solution.


"The HPC solution implemented by StarOne IT gives us the much required computing power required for running our mission critical workloads" - IT Director, Client Organization.

Overview


It is through data analysis that groundbreaking scientific discoveries are made, game-changing innovations are fueled, and quality of life is improved for billions of people around the globe. Legacy applications will have to look for opportunities to modernize IT systems to enable parallel computing to improve computing power. High-performance computing (HPC) is the ability to process data and perform complex calculations at high speeds, to fuel scientific, industrial, and societal advancements.


Challenges

Our client, which specialized in marine exploration was lacking a state-of-the-art computing solution to handle its ever-growing demand for Compute for R&D purposes. The analysis software used for computation were based on C++ and FORTRAN. The marine research cases ran on individual workstations leading to performance and infrastructure constraints. The research cases would run for long, resulting in prolonged analysis time with very limited scope of parallel executing computational tasks. Each Research case had to be manually submitted and Scientists had to wait till completion, to run the next case. These cases would require weeks to complete its run, thereby prolonging time for research & analysis, as well as decision making.


Solution Highlights


Client partnered with StarOne IT to implement a modern HPC solution to access significant computational power for research operations. StarOne IT team deployed a high-speed, scalable Fujitsu based HPC Solution with a computational capacity of four TFLOPS peak with four nodes. The solution enabled parallel processing of analysis and better scheduling of jobs for research activities.


Computational Capacity : 4 TFLOPS peak

No of Nodes : 10 Nodes

HPC Solution: Air Cooled Fujitsu Servers



Benefits

The HPC cluster has enabled researchers to perform complex experiments in much shorter timescales hence duration of running cases has drastically reduced. Job scheduler ensures the HPC cluster are utilized 24x7. Users just need to submit the cases; based on job priority and resource availability the scheduler runs the jobs without human intervention. Customer is able to scale compute power as per the case requirement up to four TFLOPS almost immediately.


StarOne IT Team’s expertise ensured end user could deploy their analysis software, which they had no idea to deploy on HPC. SOIT’s professional service have ensured customer did not have any unplanned downtime until date.