Active flash: towards energy-efficient, in-situ data analytics on extreme-scale machines

Modern scientific discovery is increasingly driven by large-scale supercomputing simulations, followed by data analysis tasks. These data analyses are either performed offline, on smaller-scale clusters, or in-situ, on the supercomputer itself. Both of these strategies are rife with storage and I/O bottlenecks, energy inefficiencies due to increased data movement, and increased time to solution. We propose Active Flash, a novel approach to in-situ, scientific data analysis, wherein data analysis is conducted on the solid-state device (SSD), where the data already resides. Our performance and energy models show that Active Flash has the potential to address many of the aforementioned concerns. In addition, we demonstrate an Active Flash prototype built on a commercial SSD controller, which further reaffirms the viability of our proposal.