Computational Storage

Updated August 2021

SNIA and the Compute, Memory, and Storage Initiative (CMSI) technical work and marketing initiatives are part of an exciting direction of adding computation to the normal storage features of devices and systems to realize a significant performance and infrastructure scaling advantage.

SNIA Board Member and Computational Storage TWG Co-Chair Scott Shadley surveys the technology market in this 2021 Persistent Memory + Computational Storage Summit presentation

The industry is seeing an increase in customer requirements to move compute closer to traditional storage devices and systems.  Computational Storage solutions typically target applications where the demand to process ever-growing storage workloads is outpacing traditional compute server architectures. These applications include AI, big data, content delivery, database, machine learning and many others that are used industry-wide.  

The SNIA Computational Storage Special Interest Group (SIG), a part of the CMSI,  evangelizes SNIA's technical work in computational storage, including developing white papers and webcasts, and speaking at SNIA and industry events. Check out their latest activities:

Check out the CMSI Knowledge Center and the SNIA Educational Library (search for "computational") for even more materials.

Computational storage technical work is accomplished by the SNIA Computational Storage TWG.  The TWG currently has out for public review the Computational Storage Architecture and Programming Model v0.8 rev 0, which defines recommended behavior for hardware and software that supports computational storage, and the Computational Storage API version 0.5 rev 0.  SNIA welcomes your comments on these specifications at the SNIA Feedback Portal.

A recent SNIA Storage Developer Conference presentation provides an overview of SNIA work in this area by Technical Work Group and Special Interest Group members.  Also check out a report by 451 Research on Computational Storage.