ActiveStor data storage supports 4D modelling research

It also needed to create a more positive user experience for both the 70 MINES ParisTech researchers who conduct HPC research at its Materials Research Centre and the 130 users of the system’s file-sharing applications.

“We chose ActiveStor for its unique combination of high performance, easy scalability, and simple administration,” said Gregory Sainte-Luce, IT manager at the Materials Research Centre and a member of the IT board at MINES ParisTech. “With Panasas ActiveStor, researchers save time since they no longer have to move or copy data files before they can process them. They gain productivity since there are no HPC bottlenecks to access the storage system. As a result, bandwidth is four to five times higher than before, and file-sharing is more convenient, thanks to shorter response times and higher throughput.”

The Materials Research Centre, the site of the ActiveStor deployment, conducts 4D statistical studies that assess mechanical stress occurring over time. The 4D testing process automatically creates a digital twin of the materials sample, allowing analysts to simulate performance and validate the behaviour models used by industrial partners.

The Centre’s BIGMECA initiative uses techniques based on artificial intelligence that analyse massive data sets to generate forecasts of a part's lifespan, according to its geometry and characteristics, with a methodology that combines experimentation, simulation and statistical learning.

“Analysis of extremely rich 4D data sets can take several months or even a year, and we are in the process of automating this analysis with our BIGMECA initiative,” said Henry Proudhon, a researcher at the Materials Research Centre. “We typically process 1 TB of data for each day of the experiment, with 15 to 20 days of experiments per year. An average study could require 100 HPC runs for six hours per day.”

The ActiveStor data storage appliance is a consistently fast, total-performance HPC storage solution that uses the PanFS parallel file system with Dynamic Data Acceleration technology to automatically adapt to the changing and evolving small file and mixed workloads that dominate today’s HPC and AI landscape – all at the lowest total-cost-of-ownership (TCO) and without the need for tuning or manual intervention.

“Materials research is fundamental to the discovery and development of new materials that lead to the advancement of technologies and products across a multitude of industries,” explained Jim Donovan, Chief Marketing Officer at Panasas. “The research conducted at MINES ParisTech drives amazing discoveries and we are honoured to support these critical efforts with a reliable, high-performance storage solution that’s ready to adapt to changing workload, capacity, and user requirements at a moment’s notice.”

What is materials science?

Materials scientists manipulate and change materials based on fundamental understandings of how the materials are put together; looking for connections between the underlying structure of a material, its properties, how processing changes it, and what the material can do.

Today, there are about 300,000 different known materials, but as materials scientists continue to create and combine materials in new ways, the number is almost infinite. Pioneers in materials science are designing unique materials that will bring vital new technologies within reach—everything from cost-effective fuel cells and solar panels, to quantum computers and ultralight, ultra-strong automobiles.