Los Alamos National Laboratory division leader: 'Often in large-scale scientific simulation, data is highly dimensional, even beyond the four dimensions of 3D space and time'

Business
Webp 363331772 782761080124763 6286371293111372180 n
Gary Grider | Facebook

At the 2023 Flash Memory Summit, Los Alamos National Laboratory and SK hynix are set to showcase the updated features of the ordered Key Value Store Computational Storage Device (KV-CSD), according to a press release. Building upon the previous year's collaboration, this project is an extension of the partnership between Los Alamos' High Performance Computing division and SK hynix, initially introduced at the 2022 Flash Memory Summit.

"Often in large-scale scientific simulation, data is highly dimensional, even beyond the four dimensions of 3D space and time," Gary Grider, High Performance Computing division leader at Los Alamos, said.

The recent addition of secondary index functionality to the system has brought about improvements in data retrieval speed and efficiency. By allowing an index to extend beyond the primary key into the value, the enhanced KV-CSD implementation has demonstrated significant speedups in large-scale simulation input-output tasks at Los Alamos National Laboratory, according to the release.

“Adding secondary indexing capabilities to the first-of-its-kind ordered KV-CSD device provides a way to approach data analytics of these highly dimensional simulation data. This capability will save time and energy in the understanding of the output of massive-scale computational science,” Grider said.

The advancement not only reduced the amount of data retrieved during scientific data analysis but also enabled the support of rich query types, further data reduction and the expansion of ordered point and range query capabilities, as a result of collaborative efforts between Laboratory researchers and SK hynix, according to the release.

“By combining Los Alamos’ renowned expertise in high performance computing and SK hynix’s technical excellence in storage solutions, we were able to deliver a state-of-the-art Key Value Store Computational Storage Device,” said Hoshik Kim, vice president and fellow of Memory Forest x&D at SK Hynix. “This advancement will significantly accelerate the performance of data analytics, which is critical in various fields of data-intensive scientific computing such as artificial intelligence, genomics, climate modeling and more. SK hynix is committed to driving innovation in the way data is stored and processed by fostering collaborative efforts with industry ecosystem partners.”