Computational Storage is a term for architectures that provide computation coupled with storage (called Computational Storage Functions or CSF) to offload host processing or reduce data movement. These architectures enable improvements in application performance and/or infrastructure efficiency through the insertion of compute resources (outside of the traditional compute and memory architecture) either directly into storage or between the host and the storage.
The goal of these architectures is to enable parallel computation and/or to alleviate demands on existing compute, memory, and I/O resources.

Learn more here about the SNIA Computational Storage Architecture and Programming Model and computational storage terms found in the SNIA Dictionary.
Educational materials may be found on the SNIA CMS Community Computational Storage SIG page.
Learn more about Computational Storage in SNIA's Educational Library, which includes technical speficications, webinars, videos, and presentations on Computational Storage.