“Los Alamos National Laboratory and SK hynix, a leading semiconductor innovator and memory/flash manufacturer, will demonstrate the world’s first ordered Key Value Store Computational Storage Device (KV-CSD), a result of a collaboration between Los Alamos’ High Performance Computing division and SK hynix.
The Laboratory is moving their large-scale simulation input-output (I/O) from file-based to record- and column-based, which enables analytics to be done using tools from the big data/analytics community. The Laboratory has shown 1000X speedups on analysis of simulation output by leveraging indexing to achieve data reduction on query via their DeltaFS parallel-file system technology. These indexing capabilities enable ordered range queries and point queries. Pushing indexing capabilities closer to the storage devices can save orders of magnitude of data movement upon retrieval for analysis.
In a first for the nonvolatile memory express industry, system researchers at SK hynix achieved pushing indexing capability functionality into the new KV-CSD prototype to mate with Laboratory security science applications.
“Moving our large-scale physics simulations from file-based I/O to record- and columnar-indexed I/O has shown incredible speedups for analysis of simulation output,” said Gary Grider, High Performance Computing division leader at Los Alamos. “Demonstrations like this show it is possible to build an ordered KV-CSD that moves the ordering and indexing of data as close to the storage device as possible, maximizing the wins on retrieval from on-the-fly indexing as data is written to the storage. The ordering capability enables range queries that are particularly useful in computational science applications as well as point queries that key value storage is known for.”
“As large-scale simulation data and big data analytics grow, solutions are critical for these communities,” said Charles Ahn, head of Solution Development at SK hynix. “We are very excited about continuing our research partnership with Los Alamos on this high-performance innovation, we consider the partnership with Los Alamos an important steppingstone toward our commitment to invest and find innovative technologies that tackle memory and storage bottlenecks in traditional HPC infrastructure.”
Los Alamos National Laboratory and SK hynix have a memorandum of understanding toward the design, implementation and evaluation of the KV-CSD.”