Los Alamos National Laboratory and AirMettle have developed a data analysis tool to analyze complex information from large-scale simulation campaigns without compromising data security.
The team has created a common applications programming interface based on AirMettle’s Real-Time Smart Data Lake architecture intended to enable computational storage devices to perform in-place analytics and minimize data movement while ensuring data is safeguarded, LANL said Tuesday.
Donpaul Stephens, founder and CEO of AirMettle, said the architecture “is the first computational storage service with highly scalable in-place processing to accelerate analytics by 100 times or more and significantly reduce network traffic.”
AirMettle’s RT-SDL tool uses common data formats, such as Apache Parquet, and standard interfaces like the S3 object storage interface to perform analytics near data storage.
