Computational Storage Workloads - Implications for Datacenter Architectures | SNIA

Abstract

Xilinx is deeply involved in several computational storage products with a range of partners. From this vantage point we have identified the common elements of workloads that map well to Computations Storage Drives (CSDs), Computational Storage Processors (CSPs), and Computational Storage Arrays (CSAs). The properties of these workloads will be outlined with brief examples. As a multi-market foundational silicon company, Xilinx is also active in a wide range of other markets where designs have evolved towards the placement of workload processing at different points in hardware designs. The reasons for where these are placed has an interesting implication on potential future datacenter architectures once the workloads that are aligned with computational storage are considered. Our prediction on how the computational storage trend and rack disaggregation intersect will be presented.